Polymarket

2 deployments · $437.6M aggregate TVL · Prediction Market

Deployments

Each deployment is rated independently. Pick one to see its rating, risk analysis, and stage.

TVL $437.6M

Type Prediction Market

Chain Polygon

View on DeFiLlama ↗

Control Exit Autonomy Open Access Verifiable

Tier silver Weak AI consensus on all dimensions
Verifiability tentative V1 audited, V2 audit coverage unconfirmed
Control tentative Untimelocked admin controls pause fees and upgrades
Ability to exit tentative Resolved exits permissionless; pending resolution pausable
Autonomy tentative UMA oracle and operator matching dependencies
Open Access tentative Permissionless contracts with independent access paths

Control criteria

Upgradeability Mixed Bug bounty cantina.xyz Governance forum — Docs docs.polymarket.com

About

Polymarket International is a prediction-market protocol on Polygon where users buy/sell ERC-1155 outcome shares (YES/NO) issued by Gnosis Conditional Tokens against an ERC-20 collateral. Markets are resolved by an UMA Optimistic Oracle adapter that writes payouts to the CTF, after which users can permissionlessly redeem winning shares for collateral. Trading uses a hybrid central limit order book: users sign orders off-chain to Polymarket's operator and the operator settles matched orders on-chain via the CTF Exchange. Version 2 (April 2026) introduces pUSD (Polymarket USD), a UUPS-upgradeable wrapper around USDC/USDC.e used as the new exchange collateral.

Risk analysis

One card per dimension, sorted by severity. Only Verifiability and Autonomy carry automated signals in Phase 0. See methodology for scope.

Audit a dimension yourself · DEFI@home Contribute an LLM-run assessment — any model, any dimension. Three agreeing runs merge automatically into the public record.

DEFI@home is a distributed audit network modeled on SETI@home: instead of CPU cycles, it crowdsources LLM reasoning. Paste a slice prompt into Claude, ChatGPT, Gemini, or any browsing-capable model, and submit the JSON output as a pull request. The quorum bot merges it once ≥3 independent runs (from different models) reach the same grade — no single model, and no single contributor, can move the needle alone. How it works →

Address discovery 15 addresses on file · 1 run Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-international
- protocol.name:              Polymarket International
- protocol.chains:            Polygon
- protocol.category:          Prediction Market
- protocol.website:           https://polymarket.com/?r=defillamareal
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               [
  {
    "chain": "Polygon",
    "address": "0xE111180000d2663C0091e4f400237545B87B996B",
    "role": "CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xe2222d279d744050d28e00520010520000310F59",
    "role": "Neg Risk CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296",
    "role": "Neg Risk Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0x4D97DCd97eC945f40cF65F87097ACe5EA0476045",
    "role": "Conditional Tokens (CTF)"
  },
  {
    "chain": "Polygon",
    "address": "0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB",
    "role": "pUSD CollateralToken (proxy)"
  },
  {
    "chain": "Polygon",
    "address": "0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f",
    "role": "pUSD CollateralToken (implementation)"
  },
  {
    "chain": "Polygon",
    "address": "0x93070a847efEf7F70739046A929D47a521F5B8ee",
    "role": "CollateralOnramp"
  },
  {
    "chain": "Polygon",
    "address": "0x2957922Eb93258b93368531d39fAcCA3B4dC5854",
    "role": "CollateralOfframp"
  },
  {
    "chain": "Polygon",
    "address": "0xebC2459Ec962869ca4c0bd1E06368272732BCb08",
    "role": "PermissionedRamp"
  },
  {
    "chain": "Polygon",
    "address": "0xAdA100Db00Ca00073811820692005400218FcE1f",
    "role": "CtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xadA2005600Dec949baf300f4C6120000bDB6eAab",
    "role": "NegRiskCtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xaacfeea03eb1561c4e67d661e40682bd20e3541b",
    "role": "Gnosis Safe Factory"
  },
  {
    "chain": "Polygon",
    "address": "0xaB45c5A4B0c941a2F231C04C3f49182e1A254052",
    "role": "Polymarket Proxy Factory"
  },
  {
    "chain": "Polygon",
    "address": "0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74",
    "role": "UMA Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0xCB1822859cEF82Cd2Eb4E6276C7916e692995130",
    "role": "UMA Optimistic Oracle"
  }
]

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
- https://defipunkd.com/address/137/0xE111180000d2663C0091e4f400237545B87B996B (CTF Exchange)
- https://defipunkd.com/address/137/0xe2222d279d744050d28e00520010520000310F59 (Neg Risk CTF Exchange)
- https://defipunkd.com/address/137/0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296 (Neg Risk Adapter)
- https://defipunkd.com/address/137/0x4D97DCd97eC945f40cF65F87097ACe5EA0476045 (Conditional Tokens (CTF))
- https://defipunkd.com/address/137/0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB (pUSD CollateralToken (proxy))
- https://defipunkd.com/address/137/0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f (pUSD CollateralToken (implementation))
- https://defipunkd.com/address/137/0x93070a847efEf7F70739046A929D47a521F5B8ee (CollateralOnramp)
- https://defipunkd.com/address/137/0x2957922Eb93258b93368531d39fAcCA3B4dC5854 (CollateralOfframp)
- https://defipunkd.com/address/137/0xebC2459Ec962869ca4c0bd1E06368272732BCb08 (PermissionedRamp)
- https://defipunkd.com/address/137/0xAdA100Db00Ca00073811820692005400218FcE1f (CtfCollateralAdapter)
- https://defipunkd.com/address/137/0xadA2005600Dec949baf300f4C6120000bDB6eAab (NegRiskCtfCollateralAdapter)
- https://defipunkd.com/address/137/0xaacfeea03eb1561c4e67d661e40682bd20e3541b (Gnosis Safe Factory)
- https://defipunkd.com/address/137/0xaB45c5A4B0c941a2F231C04C3f49182e1A254052 (Polymarket Proxy Factory)
- https://defipunkd.com/address/137/0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74 (UMA Adapter)
- https://defipunkd.com/address/137/0xCB1822859cEF82Cd2Eb4E6276C7916e692995130 (UMA Optimistic Oracle)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: DISCOVERY

You are a cataloguer, not a judge. Your job is to surface every contract address that could plausibly belong to this protocol's control or fund-holding surface, each backed by a citation. `grade` is ALWAYS `"unknown"` for discovery submissions — there is no green/orange/red rubric here. The five evaluation slices that run after you (control, ability-to-exit, autonomy, open-access, verifiability) consume your output via the addressBook ratchet — every address you record becomes a pre-built surfacer URL on the next run; every address you miss costs them a tool call.

Width beats depth. A `role: "other"` entry with one cited URL beats omitting it. Downstream slices will discard out-of-scope entries; they cannot rediscover what you fail to enumerate without paying the same cost again.

(Step 0 capability probe lives in the preamble — those rules apply here.)

### MANDATORY INSPECTION CHECKLIST (every D-code below must appear in evidence[] OR unknowns[])

- **D1. Block-explorer name-tag search per chain.** For each chain in `protocol.chains`, search the canonical block explorer for the protocol's name tag — `https://etherscan.io/searchHandler?term=<query>` and the per-chain explorers (basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network). When direct fetch is blocked, use `site:<explorer> <protocol_name>` via search grounding. Record every address that surfaces with the protocol's tag, plus neighbouring "Token Contract" / "Multisig" / "Timelock" labels.

- **D2. Official deployments doc.** From `protocol.website` and the docs site, locate the canonical "Deployed contracts" / "Addresses" / "Contracts" / "Deployments" page (often at `/docs/deployments`, `/docs/addresses`, `/dashboard/contracts`). Cite the URL, record every address listed with its named role, and set `protocol_metadata.deployed_contracts_doc` to this URL.

- **D3. Audit PDFs.** From `protocol.audit_links` (and any audits surfaced by D2), open each. Most reports include a "Scope" / "Contracts in scope" address table in the first 5 pages. Extract every in-scope address with its labelled role. If the audit predates the current deployment, record the addresses anyway with role suffixed `(audit-era)` so downstream slices know to re-verify.

- **D4. GitHub deployment artifacts.** From `protocol.github`, walk the repo at a pinned commit SHA looking for: Foundry `broadcast/<script>/<chainId>/run-latest.json` (`transactions[].contractAddress` per chainId); hardhat-deploy `deployments/<network>/<Contract>.json` (`address` field); manual indexes (`deployments.json`, `addresses.json`, `contracts.json`, `networks.json`); markdown indexes (`docs/deployments.md`, `README.md` tables). Cite the file URL with the commit SHA; pin SHAs (`?ref=<sha>`) so the citation is content-addressed.

- **D5. Multi-chain enumeration.** If `protocol.chains.length > 1`, repeat D1–D4 per chain. Cross-chain deployments of the same logical contract get SEPARATE `admin_addresses[]` entries — one per chain. The chain field is part of the identity; do not collapse. If a chain has zero results, record `"D5: chain <name>: zero addresses surfaced from <sources tried>"` in unknowns[].

- **D6. Factory-discovered children.** For factory addresses surfaced in D1–D4, fetch the enumeration view via the read API (`/api/contract/read?...&method=allPools` / `getPool` / `getMarket` / `getVault`) and record each child with role like `"pool (from factory <0xFactory>)"`. **Cap at 50 children per factory.** Protocols with thousands of pools (Uniswap, Sushi) need dedicated ingestion — record the factory + the cap notice in unknowns[].

- **D7. Role taxonomy.** Every `admin_addresses[]` entry's `role` uses this controlled vocabulary (free-text suffixes OK for disambiguation, e.g. `"multisig (treasury)"`, but the leading token must match):

    `owner | admin | proxy_admin | governor | timelock | guardian | multisig | treasury | oracle | factory | router | token | pool | vault | other`

  Tentative classifications are encouraged. `actor_class` ∈ `eoa | multisig | timelock | governance | unknown` — use `unknown` when you found the address but didn't read its bytecode.

- **D8. Ratchet output integrity.** Every address in `admin_addresses[]` must trace to ≥1 fetched URL in evidence[]. Snippet-only sightings go in unknowns[] with a `D8` code, NOT in admin_addresses[].

### Discovery rationale framing

- `rationale.findings`: one entry per D-code, terse, factual. Per-address detail belongs in evidence[] and admin_addresses[], not here. Example: `"D1: 8 addresses surfaced from etherscan.io name-tag search for 'Aave V3'"`.
- `rationale.steelman`: ALWAYS null.
- `rationale.verdict`: one short line summarizing what corpora were walked and how many addresses were catalogued.
- `headline`: factual and quantitative — `"24 contracts catalogued across Ethereum, Arbitrum, and Base; 6 governance/admin and 18 protocol contracts."`.
- `short_headline`: under 60 chars — `"24 contracts across 3 chains"`.

### What discovery is NOT

- Not a verdict slice. `grade` must be `"unknown"`.
- Not exhaustive enumeration of leaf assets — record the factory + cap and move on (see D6).
- Not classification of trust assumptions — whether a multisig threshold is safe / timelock delay is sufficient / proxy admin is an EOA is the control slice's job.
- Not address-book reconciliation: when addressBook is non-empty, EXTEND it (find addresses prior runs missed) rather than re-cite the same addresses; re-cite only when you have new evidence for a refined role.

### protocol_metadata side-effects

While walking the corpora, populate every `protocol_metadata` field you can support with citations: `github`, `docs_url`, `audits` (one per D3 audit walked), `governance_forum`, `bug_bounty_url`, `security_contact`, `deployed_contracts_doc` (URL from D2), `upgradeability` (best-effort), and `about` (2–4 sentences sourced from docs/website, not memory). Discovery is the natural home for these — evaluation slices should not have to rediscover them.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "discovery",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Verifiability ✓ 3/3 models agree AI-only weak orange — weak consensus margin Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-international
- protocol.name:              Polymarket International
- protocol.chains:            Polygon
- protocol.category:          Prediction Market
- protocol.website:           https://polymarket.com/?r=defillamareal
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               [
  {
    "chain": "Polygon",
    "address": "0xE111180000d2663C0091e4f400237545B87B996B",
    "role": "CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xe2222d279d744050d28e00520010520000310F59",
    "role": "Neg Risk CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296",
    "role": "Neg Risk Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0x4D97DCd97eC945f40cF65F87097ACe5EA0476045",
    "role": "Conditional Tokens (CTF)"
  },
  {
    "chain": "Polygon",
    "address": "0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB",
    "role": "pUSD CollateralToken (proxy)"
  },
  {
    "chain": "Polygon",
    "address": "0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f",
    "role": "pUSD CollateralToken (implementation)"
  },
  {
    "chain": "Polygon",
    "address": "0x93070a847efEf7F70739046A929D47a521F5B8ee",
    "role": "CollateralOnramp"
  },
  {
    "chain": "Polygon",
    "address": "0x2957922Eb93258b93368531d39fAcCA3B4dC5854",
    "role": "CollateralOfframp"
  },
  {
    "chain": "Polygon",
    "address": "0xebC2459Ec962869ca4c0bd1E06368272732BCb08",
    "role": "PermissionedRamp"
  },
  {
    "chain": "Polygon",
    "address": "0xAdA100Db00Ca00073811820692005400218FcE1f",
    "role": "CtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xadA2005600Dec949baf300f4C6120000bDB6eAab",
    "role": "NegRiskCtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xaacfeea03eb1561c4e67d661e40682bd20e3541b",
    "role": "Gnosis Safe Factory"
  },
  {
    "chain": "Polygon",
    "address": "0xaB45c5A4B0c941a2F231C04C3f49182e1A254052",
    "role": "Polymarket Proxy Factory"
  },
  {
    "chain": "Polygon",
    "address": "0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74",
    "role": "UMA Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0xCB1822859cEF82Cd2Eb4E6276C7916e692995130",
    "role": "UMA Optimistic Oracle"
  }
]

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
- https://defipunkd.com/address/137/0xE111180000d2663C0091e4f400237545B87B996B (CTF Exchange)
- https://defipunkd.com/address/137/0xe2222d279d744050d28e00520010520000310F59 (Neg Risk CTF Exchange)
- https://defipunkd.com/address/137/0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296 (Neg Risk Adapter)
- https://defipunkd.com/address/137/0x4D97DCd97eC945f40cF65F87097ACe5EA0476045 (Conditional Tokens (CTF))
- https://defipunkd.com/address/137/0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB (pUSD CollateralToken (proxy))
- https://defipunkd.com/address/137/0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f (pUSD CollateralToken (implementation))
- https://defipunkd.com/address/137/0x93070a847efEf7F70739046A929D47a521F5B8ee (CollateralOnramp)
- https://defipunkd.com/address/137/0x2957922Eb93258b93368531d39fAcCA3B4dC5854 (CollateralOfframp)
- https://defipunkd.com/address/137/0xebC2459Ec962869ca4c0bd1E06368272732BCb08 (PermissionedRamp)
- https://defipunkd.com/address/137/0xAdA100Db00Ca00073811820692005400218FcE1f (CtfCollateralAdapter)
- https://defipunkd.com/address/137/0xadA2005600Dec949baf300f4C6120000bDB6eAab (NegRiskCtfCollateralAdapter)
- https://defipunkd.com/address/137/0xaacfeea03eb1561c4e67d661e40682bd20e3541b (Gnosis Safe Factory)
- https://defipunkd.com/address/137/0xaB45c5A4B0c941a2F231C04C3f49182e1A254052 (Polymarket Proxy Factory)
- https://defipunkd.com/address/137/0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74 (UMA Adapter)
- https://defipunkd.com/address/137/0xCB1822859cEF82Cd2Eb4E6276C7916e692995130 (UMA Optimistic Oracle)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: VERIFIABILITY

Evaluate whether an outsider can independently confirm what the deployed code does.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- V1. For each address you assess: is the bytecode verified on the chain's block explorer? Record the "Contract Source Code Verified" indicator. https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x... returns this as a top-level "verified" boolean plus "abiSource" ("etherscan" / "sourcify") and an inline ABI — useful when the explorer page is rate-limited. If the contract is a proxy, verify BOTH the proxy contract AND the current implementation contract. The same /api/contract/abi response auto-resolves proxies and includes a "proxy.implementation" address when present, so one call covers V1 + V6 in one shot. An explorer "Similar Match" on a well-known proxy pattern (Aragon AppProxyUpgradeable, ERC1967Proxy, OssifiableProxy, OZ TransparentUpgradeableProxy) is expected for that pattern and does NOT count as a verification gap on its own — what matters is that the implementation is independently verified.
- V2. Source-to-repo correspondence: for each verified contract, attempt to find a matching commit in the linked GitHub repos. Record evidence[].commit on a match. Independent compile/bytecode-match is NOT required for green — a recognized public repo whose structure and file contents correspond to the explorer-visible source is sufficient. If you did not pin a commit SHA or run a bytecode diff, record that plainly in unknowns[] and proceed; it is a scope limit, not a downgrade signal.
- V3. Audit coverage: for each URL in protocol.audit_links, open it and record: auditor name, audit date, the specific contracts / commit in scope. Flag audits that predate the current deployment by >6 months without a follow-up review.
- V4. Auditor recognition: the following firms are broadly recognized in Solidity: Trail of Bits, Zellic, Spearbit, OpenZeppelin, ConsenSys Diligence, Certora (formal verification), Quantstamp, Halborn, Peckshield, Sigma Prime, ChainSecurity, Ackee Blockchain, MixBytes, Statemind. Unknown firms are orange-at-best for any green-grade claim. Name the firm explicitly in evidence[].
- V5. Post-audit drift: compare the most recent in-scope audit(s) against the currently-deployed source, weighted by what each contract does and by what the changes actually contain. SCOPE — drift only downgrades the grade when ALL of the following hold: (i) the drifting contract is fund-custody / settlement / accounting-critical (NOT a peripheral router, lens, quoter, or pure-view contract that holds no balances); (ii) the changes are material — new functions, modified access control, modified accounting, modified fund flow — and not refactors / struct relocations / import reorgs / build or CI fixes / formatting; (iii) no later audit, fix-audit, or differential audit from a recognized firm covers the changed files (audits often pin a pre-fix commit while a follow-up reviews the delta — match by file scope, not by commit-hash equality). When you cite drift as a downgrade reason, name the specific behavior change (function added, role granted, accounting formula altered) — "N commits ahead" or "+X/-Y LOC" alone is not evidence of material drift. If you have not sampled the diff content (e.g. via the GitHub compare view or the top commits in the window), record drift as an unknowns[] entry rather than auto-downgrading; commit-count and LOC are starting signals, not findings.
- V6. Implementation vs proxy: a verified proxy with an unverified implementation is effectively unverified. State whether the implementation is verified separately.

EVIDENCE DISCIPLINE (read before writing findings[]):
- Do not assert a specific deploy-commit SHA, bytecode equivalence, or "identical to audited commit" unless you actually fetched the artifact that shows it (e.g., a deployed-addresses JSON you opened, an explorer page you read). Inferred or plausible matches belong in unknowns[], never in findings[] or evidence[].
- Evidence[] entries must correspond to pages/files you actually retrieved this run. A URL you did not open is not evidence.

Then write the steel-man section per Hard Rule 11.

Grade rules:
- green   = deployed bytecode verified on the explorer (proxy AND implementation if proxied; "Similar Match" on a standard proxy pattern is fine per V1), a public source repo exists whose contents correspond to the explorer-visible source, AND ≥1 audit from a recognized firm covering the currently-deployed contracts (≤6 months of drift OR drift was re-audited). A missing local compile-match is not a downgrade — record it in unknowns[] and still grade green if the other conditions hold.
- orange  = verified but with visible drift from the public repo, OR audit scope is stale relative to deployment, OR only minor / unknown-firm audits exist, OR only some of the main contracts are verified, OR proxy verified but implementation only partially verified.
- red     = unverified bytecode (or verified proxy with unverified implementation), OR no audit in protocol.audit_links, OR no public repo.
- unknown = reserved for when the protocol's verifiability posture genuinely cannot be assessed (e.g., explorer and repo both inaccessible for this protocol). Do NOT use unknown merely because you, the analyst, could not run a particular check such as a bytecode diff — that goes in unknowns[] while the grade is still assigned from the evidence you do have.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "verifiability",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Control ✓ 3/3 models agree AI-only weak orange — weak consensus margin Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-international
- protocol.name:              Polymarket International
- protocol.chains:            Polygon
- protocol.category:          Prediction Market
- protocol.website:           https://polymarket.com/?r=defillamareal
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               [
  {
    "chain": "Polygon",
    "address": "0xE111180000d2663C0091e4f400237545B87B996B",
    "role": "CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xe2222d279d744050d28e00520010520000310F59",
    "role": "Neg Risk CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296",
    "role": "Neg Risk Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0x4D97DCd97eC945f40cF65F87097ACe5EA0476045",
    "role": "Conditional Tokens (CTF)"
  },
  {
    "chain": "Polygon",
    "address": "0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB",
    "role": "pUSD CollateralToken (proxy)"
  },
  {
    "chain": "Polygon",
    "address": "0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f",
    "role": "pUSD CollateralToken (implementation)"
  },
  {
    "chain": "Polygon",
    "address": "0x93070a847efEf7F70739046A929D47a521F5B8ee",
    "role": "CollateralOnramp"
  },
  {
    "chain": "Polygon",
    "address": "0x2957922Eb93258b93368531d39fAcCA3B4dC5854",
    "role": "CollateralOfframp"
  },
  {
    "chain": "Polygon",
    "address": "0xebC2459Ec962869ca4c0bd1E06368272732BCb08",
    "role": "PermissionedRamp"
  },
  {
    "chain": "Polygon",
    "address": "0xAdA100Db00Ca00073811820692005400218FcE1f",
    "role": "CtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xadA2005600Dec949baf300f4C6120000bDB6eAab",
    "role": "NegRiskCtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xaacfeea03eb1561c4e67d661e40682bd20e3541b",
    "role": "Gnosis Safe Factory"
  },
  {
    "chain": "Polygon",
    "address": "0xaB45c5A4B0c941a2F231C04C3f49182e1A254052",
    "role": "Polymarket Proxy Factory"
  },
  {
    "chain": "Polygon",
    "address": "0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74",
    "role": "UMA Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0xCB1822859cEF82Cd2Eb4E6276C7916e692995130",
    "role": "UMA Optimistic Oracle"
  }
]

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
- https://defipunkd.com/address/137/0xE111180000d2663C0091e4f400237545B87B996B (CTF Exchange)
- https://defipunkd.com/address/137/0xe2222d279d744050d28e00520010520000310F59 (Neg Risk CTF Exchange)
- https://defipunkd.com/address/137/0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296 (Neg Risk Adapter)
- https://defipunkd.com/address/137/0x4D97DCd97eC945f40cF65F87097ACe5EA0476045 (Conditional Tokens (CTF))
- https://defipunkd.com/address/137/0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB (pUSD CollateralToken (proxy))
- https://defipunkd.com/address/137/0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f (pUSD CollateralToken (implementation))
- https://defipunkd.com/address/137/0x93070a847efEf7F70739046A929D47a521F5B8ee (CollateralOnramp)
- https://defipunkd.com/address/137/0x2957922Eb93258b93368531d39fAcCA3B4dC5854 (CollateralOfframp)
- https://defipunkd.com/address/137/0xebC2459Ec962869ca4c0bd1E06368272732BCb08 (PermissionedRamp)
- https://defipunkd.com/address/137/0xAdA100Db00Ca00073811820692005400218FcE1f (CtfCollateralAdapter)
- https://defipunkd.com/address/137/0xadA2005600Dec949baf300f4C6120000bDB6eAab (NegRiskCtfCollateralAdapter)
- https://defipunkd.com/address/137/0xaacfeea03eb1561c4e67d661e40682bd20e3541b (Gnosis Safe Factory)
- https://defipunkd.com/address/137/0xaB45c5A4B0c941a2F231C04C3f49182e1A254052 (Polymarket Proxy Factory)
- https://defipunkd.com/address/137/0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74 (UMA Adapter)
- https://defipunkd.com/address/137/0xCB1822859cEF82Cd2Eb4E6276C7916e692995130 (UMA Optimistic Oracle)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: CONTROL

Evaluate who can change the protocol's rules, how fast, and how broadly.

(Step 0 capability probe and the off-chain-only fallback live in the preamble — those rules apply here.)

### MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[])

- **C1.** For each address you assess: who is the contract owner / admin / pendingAdmin / governor — read these via the block explorer's "Read Contract" tab OR `https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=owner` (BARE method names: `&method=owner`, `&method=admin`, `&method=pendingOwner`, `&method=governor`). For Safes use `/api/safe/owners?chainId=<id>&address=0x...`. When a protocol has multiple major versions deployed (v2/v3/v4), perform C1 reads on the NEWEST deployment separately — newer deployments often have weaker control surfaces than the legacy core.
- **C2.** Upgrade mechanism: transparent proxy / UUPS / Beacon / Diamond / immutable. Identify the proxy admin address. Check upgradeability of GOVERNANCE contracts too — a Governor / Aragon Voting / OZ Governor is often itself a proxy whose admin is the Timelock. Asymmetry: when fund-holding cores are immutable AND governance has no admin path that reaches them, an upgradable Governor/Timelock is T3-only and must NOT drag the verdict below green on that basis alone (see grade rules and the "immutable cores" caveat). Only call upgradability "mixed" if you can name a concrete function on the upgradable surface that reaches T1 or T2 on user funds.
- **C3.** EXECUTION PATH (enumerate every stage, in order, with delays in seconds). The operative path is usually a chain (voting → scheduler → timelock → executor; or governor → queue → execute; or Aragon Voting → DualGovernance → EmergencyProtectedTimelock → AdminExecutor). For each stage, record (a) the contract address, (b) the delay constant name + value in seconds, (c) the URL you read it from (block-explorer Read Contract OR `/api/contract/read?...&method=MIN_DELAY&block=<n>`). Do NOT stop at the first timelock-shaped contract — if its admin is itself called by another contract, keep walking. The grading delay is the SUM OF DELAYS ON THE UNCONTESTED FAST PATH (shortest time a proposal with no opposition can go from submission to executable). Dynamic / contested extensions (veto signaling, rage quit, escrow delay) are modifiers, not the basis — note them separately.
- **C4.** Enumerate EVERY multisig with reachable control — main proxy admin, emergency activation, emergency execution, reseal / pause, gate-seal committees, tiebreaker, per-module admins. For each Safe, fetch threshold + owners + version via `/api/safe/owners?chainId=<id>&address=0x...` (response includes raw eth_call data, so the URL is citable evidence). Enumerate ops/council/incentives multisigs even when off the upgrade path — record their scope so a reader can see they are NOT on the upgrade path. For each: (a) address, (b) threshold / total signers, (c) signer identities classified as insider (team, paid auditors under ongoing engagement, mandated service providers) vs non-insider (independent community members, unaffiliated researchers), (d) the specific power held (upgrade, pause, parameter, etc.).
- **C5.** On-chain governance: Governor / GovernorBravo / OZ Governor / Aragon Voting with token-weighted voting? Record proposal threshold, voting period, quorum, and the timelock delay between queue and execute. Every numeric constant must come from a Read Contract call you can link to, or be in unknowns[] with the C-code. If votingDelay / votingPeriod are denominated in BLOCKS, convert to seconds at the chain's CURRENT block time (Ethereum mainnet ≈ 12s post-Merge, not the 15s in older Compound/Bravo deployments) — cite both block count and converted seconds.
- **C6.** EMERGENCY POWERS: separate emergency-pause / guardian role with a different time cap or different actor than the main upgrade authority? Record it explicitly.
- **C7.** POWER TIER (blast radius). For each privileged path in C3–C6, classify the WORST thing that path can do, choosing the highest applicable tier. Cite the specific function name and any on-chain bound — tier claims without a named function are unsupported.
    - **T1 — FUND-CRITICAL**: replace implementation of contracts holding user funds; change AMM math / accounting / collateral logic; mint unbacked debt or shares; pause withdrawals; drain user-fund treasury; change oracle to attacker-controlled source; replace upgrade admin with EOA.
    - **T2 — ECONOMICALLY MATERIAL**: change fee parameters within bounded ranges; redirect protocol fees; add/remove markets / collateral types; bounded inflation or token mint within hard-capped schedule; spend protocol-owned (non-user) treasury.
    - **T3 — GOVERNANCE-INTERNAL**: change voting rules, quorum, voting period, proposal threshold; upgrade the Governor itself; rotate Timelock admin; mint governance tokens within a capped annual schedule.
    - **T4 — OPERATIONAL**: incentives distribution, grants, ENS / frontend canonicalization, deployment coordination, periphery router deprecation.
  The grade is set by the HIGHEST tier reachable on the uncontested fast path, not the median. State the tier and the binding function in the verdict.

### Read Contract discipline (applies to C3, C4, C5)

Every numeric constant cited (timelock delays, voting periods, multisig thresholds, quorum percentages) must come from EITHER (a) a block-explorer Read Contract URL, OR (b) a DeFiPunkd `/api/contract/read` or `/api/safe/owners` URL (preferred with `&block=<n>` for content-addressed evidence), OR (c) an unknowns[] entry with the C-code. Docs / blog posts are corroboration only — they cannot be the sole citation for a value that is also readable on-chain.

### Off-chain-only substitute hierarchy (when grading_basis="off-chain-only" — see preamble Rule 16)

When on-chain reads were genuinely unreachable this run, eligible off-chain substitutes in priority order:
1. Linked audit PDFs (admin roles, multisig members, timelock delays usually enumerated).
2. Governance forum posts that quote constants from a successful on-chain proposal (cite post URL + linked execution-tx URL).
3. Official protocol docs pages with named addresses and roles (must be on a domain owned by the protocol).
4. GitHub README / SECURITY.md / governance/*.md at a pinned commit SHA.

Forbidden substitutes: third-party blog posts, X / Twitter threads, search-result snippets, model memory. Required degradation: any C-code citing a numeric constant from docs/forum/audit prose ONLY must also carry an `unknowns[]` entry with `-offchain` suffix noting "value not re-read on-chain in this run; corroboration only".

### Grade rules (apply the timelock bar conditional on the highest C7 tier reachable on the fast path)

Security Council standard (used below): a multisig qualifies as "Security Council" only if ALL of: ≥7 signers, ≥51% threshold, ≥50% non-insider signers, every signer publicly announced. Failing any criterion = NOT a Security Council, regardless of signer reputation.

- **green**: highest reachable tier is T3 or T4 regardless of timelock; OR T2 reachable with uncontested-fast-path delay ≥7 days; OR T1 reachable only via immutable contracts (T1 is unreachable); OR T1 reachable with uncontested-fast-path delay ≥7 days combined with a Security Council multisig; OR T1 reachable with uncontested-fast-path delay ≥7 days through active on-chain governance with broad token distribution.
- **orange**: T2 reachable with uncontested-fast-path delay >0 but <7 days; OR T1 reachable with uncontested-fast-path delay >0 but <7 days; OR a multisig failing one or more Security Council criteria sits on a T1/T2 path; OR unclear upgrade authority on a T1/T2 path; OR governance with very short timelock or low quorum on a T1/T2 path.
- **red**: T1 reachable with no timelock by a single EOA or 2-of-3 multisig; OR a T1 upgrade admin that is not a smart contract you can audit.
- **unknown**: completed the checklist but still cannot determine the upgrade authority OR cannot classify the highest tier reachable on the main contracts.

Tiering caveats:
- "Bounded" must be enforced ON-CHAIN to count as T2. A function that sets fees with no upper-bound check is T1 — cite the bound check.
- Recurring T2 economic extraction (e.g. fee redirect with no rate limit) approaches T1 over time. A single proposal that can permanently redirect all future revenue is T1.
- T3 assumes the governance contract cannot itself authorize a T1/T2 action without going through the same timelock. If governance can self-upgrade to bypass the timelock, T3 collapses into T1.
- Do not downgrade tier by hand-waving ("realistically governance would never…"). Tier on what the contract permits, not what feels likely.

Notes:
- **Dynamic / dual-governance timelocks** (Lido, Compound escrow veto): the rubric grades on the uncontested path because that is the path most upgrades take. A dynamic extension that fires only under stake-weighted opposition is a real protection — name it in the green steel-man, but it does not lift an orange fast path into green; state the tension in the verdict.
- **Immutable cores with upgradable governance** (Uniswap-style): if fund-holding contracts are immutable and have no admin-reachable function moving / freezing / re-routing user funds, the highest reachable tier on the upgrade path is T3 — green regardless of timelock. Don't grade this orange just because the Governor is a proxy — that's a C2 fact, not a downgrade. Downgrade only applies if you can cite a concrete function on the upgradable surface that reaches T1 or T2 (privileged hook, upgradable factory controlling fund-routing, fee-switch redirecting protocol revenue without bound).
- **The 7-day bar** reflects the exit-window standard — users need notice after a queued upgrade to withdraw if they disagree. The ability-to-exit slice grades the exit side; this slice grades the delay side; both must hold for users to actually benefit from the delay.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "control",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Ability to exit ✓ 3/3 models agree AI-only weak orange — weak consensus margin Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-international
- protocol.name:              Polymarket International
- protocol.chains:            Polygon
- protocol.category:          Prediction Market
- protocol.website:           https://polymarket.com/?r=defillamareal
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               [
  {
    "chain": "Polygon",
    "address": "0xE111180000d2663C0091e4f400237545B87B996B",
    "role": "CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xe2222d279d744050d28e00520010520000310F59",
    "role": "Neg Risk CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296",
    "role": "Neg Risk Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0x4D97DCd97eC945f40cF65F87097ACe5EA0476045",
    "role": "Conditional Tokens (CTF)"
  },
  {
    "chain": "Polygon",
    "address": "0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB",
    "role": "pUSD CollateralToken (proxy)"
  },
  {
    "chain": "Polygon",
    "address": "0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f",
    "role": "pUSD CollateralToken (implementation)"
  },
  {
    "chain": "Polygon",
    "address": "0x93070a847efEf7F70739046A929D47a521F5B8ee",
    "role": "CollateralOnramp"
  },
  {
    "chain": "Polygon",
    "address": "0x2957922Eb93258b93368531d39fAcCA3B4dC5854",
    "role": "CollateralOfframp"
  },
  {
    "chain": "Polygon",
    "address": "0xebC2459Ec962869ca4c0bd1E06368272732BCb08",
    "role": "PermissionedRamp"
  },
  {
    "chain": "Polygon",
    "address": "0xAdA100Db00Ca00073811820692005400218FcE1f",
    "role": "CtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xadA2005600Dec949baf300f4C6120000bDB6eAab",
    "role": "NegRiskCtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xaacfeea03eb1561c4e67d661e40682bd20e3541b",
    "role": "Gnosis Safe Factory"
  },
  {
    "chain": "Polygon",
    "address": "0xaB45c5A4B0c941a2F231C04C3f49182e1A254052",
    "role": "Polymarket Proxy Factory"
  },
  {
    "chain": "Polygon",
    "address": "0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74",
    "role": "UMA Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0xCB1822859cEF82Cd2Eb4E6276C7916e692995130",
    "role": "UMA Optimistic Oracle"
  }
]

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
- https://defipunkd.com/address/137/0xE111180000d2663C0091e4f400237545B87B996B (CTF Exchange)
- https://defipunkd.com/address/137/0xe2222d279d744050d28e00520010520000310F59 (Neg Risk CTF Exchange)
- https://defipunkd.com/address/137/0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296 (Neg Risk Adapter)
- https://defipunkd.com/address/137/0x4D97DCd97eC945f40cF65F87097ACe5EA0476045 (Conditional Tokens (CTF))
- https://defipunkd.com/address/137/0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB (pUSD CollateralToken (proxy))
- https://defipunkd.com/address/137/0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f (pUSD CollateralToken (implementation))
- https://defipunkd.com/address/137/0x93070a847efEf7F70739046A929D47a521F5B8ee (CollateralOnramp)
- https://defipunkd.com/address/137/0x2957922Eb93258b93368531d39fAcCA3B4dC5854 (CollateralOfframp)
- https://defipunkd.com/address/137/0xebC2459Ec962869ca4c0bd1E06368272732BCb08 (PermissionedRamp)
- https://defipunkd.com/address/137/0xAdA100Db00Ca00073811820692005400218FcE1f (CtfCollateralAdapter)
- https://defipunkd.com/address/137/0xadA2005600Dec949baf300f4C6120000bDB6eAab (NegRiskCtfCollateralAdapter)
- https://defipunkd.com/address/137/0xaacfeea03eb1561c4e67d661e40682bd20e3541b (Gnosis Safe Factory)
- https://defipunkd.com/address/137/0xaB45c5A4B0c941a2F231C04C3f49182e1A254052 (Polymarket Proxy Factory)
- https://defipunkd.com/address/137/0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74 (UMA Adapter)
- https://defipunkd.com/address/137/0xCB1822859cEF82Cd2Eb4E6276C7916e692995130 (UMA Optimistic Oracle)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: ABILITY-TO-EXIT

Evaluate whether users can withdraw their funds on their own terms, even under adversarial admin conditions.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- E1. Enumerate every user-facing exit function in the main contracts: withdraw, redeem, burn, requestWithdrawal, claim, exit, etc. List them by name. Do NOT treat the contract as a monolith.
- E2. For EACH exit function in E1: identify its access modifiers and any pause guards (e.g. _checkResumed, whenNotPaused, onlyRole). Functions that gate REQUEST PLACEMENT often differ from functions that CLAIM FINALIZED FUNDS — check both separately.
- E3. For each pause guard: identify the role holder (which address holds PAUSE_ROLE / GUARDIAN / etc.) and the maximum pause duration. Specifically check whether PAUSE_INFINITELY (or equivalent uncapped pause) is callable, and which actor can call it (single multisig vs governance vote). For role-holder reads use https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=hasRole&args=0x...,0x... or &method=getRoleAdmin&args=0x.... For "is currently paused" checks use &method=paused or &method=isPaused&args=<resume-code>. Use the BARE method name (no parens). Cite the URL with &block=<n> in evidence[].
- E4. EMERGENCY vs GOVERNANCE pause distinction: many protocols have a fast-acting emergency pause capped at N days and a slow governance pause that can be indefinite. Record both paths separately if present, with their time caps and actor classes.
- E5. Queued redemption: documented maximum queue duration, daily withdrawal caps, whether the queue itself is pausable.
- E6. Forced-exit / escape-hatch / permissionless emergency-exit mechanism for adversarial-admin scenarios.
- E7. Frontend dependency: confirm exit functions are directly callable on-chain (e.g. via Etherscan write tab or a generic wallet) without the project's frontend.

Then write the steel-man section per Hard Rule 11. Common red-vs-orange tension on this slice: indefinite pause exists (suggests red) BUT the realistic emergency path is time-capped AND claims of already-finalized exits are not pause-gated (suggests orange). Resolve this by stating who can do what for how long, not by stopping at the worst-case sentence.

Grade rules:
- green   = permissionless exit; pause is either absent, narrowly scoped to clearly-described emergencies with auto-expiry, or capped at ≤7 days; no frontend dependency for exit; claims of already-finalized exits are not pause-gated under any path.
- orange  = pausable with broad scope OR indefinite pause is reachable only through governance vote (not unilateral admin action), OR queued redemption with documented max > 7 days, OR claims-of-finalized are exempt but new-request placement can be paused indefinitely by governance.
- red     = exit requires admin signature, OR ANY actor (including governance) can pause CLAIMS of finalized exits indefinitely, OR there is no on-chain exit function at all (purely custodial), OR pause is held by a single EOA / 2-of-3 multisig with no time cap.
- unknown = checklist incomplete after checking the sources above.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "ability-to-exit",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Autonomy ✓ 3/3 models agree AI-only weak orange — weak consensus margin Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-international
- protocol.name:              Polymarket International
- protocol.chains:            Polygon
- protocol.category:          Prediction Market
- protocol.website:           https://polymarket.com/?r=defillamareal
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               [
  {
    "chain": "Polygon",
    "address": "0xE111180000d2663C0091e4f400237545B87B996B",
    "role": "CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xe2222d279d744050d28e00520010520000310F59",
    "role": "Neg Risk CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296",
    "role": "Neg Risk Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0x4D97DCd97eC945f40cF65F87097ACe5EA0476045",
    "role": "Conditional Tokens (CTF)"
  },
  {
    "chain": "Polygon",
    "address": "0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB",
    "role": "pUSD CollateralToken (proxy)"
  },
  {
    "chain": "Polygon",
    "address": "0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f",
    "role": "pUSD CollateralToken (implementation)"
  },
  {
    "chain": "Polygon",
    "address": "0x93070a847efEf7F70739046A929D47a521F5B8ee",
    "role": "CollateralOnramp"
  },
  {
    "chain": "Polygon",
    "address": "0x2957922Eb93258b93368531d39fAcCA3B4dC5854",
    "role": "CollateralOfframp"
  },
  {
    "chain": "Polygon",
    "address": "0xebC2459Ec962869ca4c0bd1E06368272732BCb08",
    "role": "PermissionedRamp"
  },
  {
    "chain": "Polygon",
    "address": "0xAdA100Db00Ca00073811820692005400218FcE1f",
    "role": "CtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xadA2005600Dec949baf300f4C6120000bDB6eAab",
    "role": "NegRiskCtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xaacfeea03eb1561c4e67d661e40682bd20e3541b",
    "role": "Gnosis Safe Factory"
  },
  {
    "chain": "Polygon",
    "address": "0xaB45c5A4B0c941a2F231C04C3f49182e1A254052",
    "role": "Polymarket Proxy Factory"
  },
  {
    "chain": "Polygon",
    "address": "0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74",
    "role": "UMA Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0xCB1822859cEF82Cd2Eb4E6276C7916e692995130",
    "role": "UMA Optimistic Oracle"
  }
]

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
- https://defipunkd.com/address/137/0xE111180000d2663C0091e4f400237545B87B996B (CTF Exchange)
- https://defipunkd.com/address/137/0xe2222d279d744050d28e00520010520000310F59 (Neg Risk CTF Exchange)
- https://defipunkd.com/address/137/0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296 (Neg Risk Adapter)
- https://defipunkd.com/address/137/0x4D97DCd97eC945f40cF65F87097ACe5EA0476045 (Conditional Tokens (CTF))
- https://defipunkd.com/address/137/0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB (pUSD CollateralToken (proxy))
- https://defipunkd.com/address/137/0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f (pUSD CollateralToken (implementation))
- https://defipunkd.com/address/137/0x93070a847efEf7F70739046A929D47a521F5B8ee (CollateralOnramp)
- https://defipunkd.com/address/137/0x2957922Eb93258b93368531d39fAcCA3B4dC5854 (CollateralOfframp)
- https://defipunkd.com/address/137/0xebC2459Ec962869ca4c0bd1E06368272732BCb08 (PermissionedRamp)
- https://defipunkd.com/address/137/0xAdA100Db00Ca00073811820692005400218FcE1f (CtfCollateralAdapter)
- https://defipunkd.com/address/137/0xadA2005600Dec949baf300f4C6120000bDB6eAab (NegRiskCtfCollateralAdapter)
- https://defipunkd.com/address/137/0xaacfeea03eb1561c4e67d661e40682bd20e3541b (Gnosis Safe Factory)
- https://defipunkd.com/address/137/0xaB45c5A4B0c941a2F231C04C3f49182e1A254052 (Polymarket Proxy Factory)
- https://defipunkd.com/address/137/0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74 (UMA Adapter)
- https://defipunkd.com/address/137/0xCB1822859cEF82Cd2Eb4E6276C7916e692995130 (UMA Optimistic Oracle)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: AUTONOMY

Evaluate this protocol's autonomy: can a failure of anything outside its own contracts cause theft or loss of user principal, loss of unclaimed yield, or materially change the protocol's expected performance? "Autonomy" is not "has zero external touchpoints" — it is "external failures are either survivable or recoverable without user loss". This slice adapts DefiScan v1's Autonomy dimension; dependencies are one of several criteria, not the whole frame.

GUARDRAILS (read before grading):
- Category alone (Liquid Staking, Bridge, RWA Lending, Restaking, …) does NOT force a grade. A category is a hint about where to look; the grade must come from the concrete A1–A9 findings below.
- Base-chain consensus (Ethereum PoS, the chain's validator set, the canonical Deposit Contract at 0x00000000219ab540356cBB839Cbe05303d7705Fa) is the SUBSTRATE, not a dependency, for any protocol deployed on that chain. Do not list "depends on Ethereum" as a finding.
- Oracles or other integrations used by DOWNSTREAM protocols that happen to read this protocol's token (e.g. Chainlink stETH/USD consumed by Aave) are NOT this protocol's dependencies. Count only what THIS protocol's contracts call or trust on-chain. If a feed or contract appears in the protocol's docs only as reference material for third-party integrators, EXCLUDE IT ENTIRELY — do not log it as a finding even with a "peripheral" or "referenced only" caveat.
- "Upgradeable admin can change things" belongs to the CONTROL slice; only count it here when the upgrade surface lets governance silently swap an external dependency (see A9).
- Underlying-asset risk in opt-in, isolated markets is NOT autonomy-red on its own. When a protocol wraps third-party yield-bearing assets (LSTs, LRTs, ERC-4626 vaults, lending receipts, restaked tokens) into per-market silos that users explicitly choose, a failure of one underlying does NOT propagate to other markets and is risk the user opted into per-market. Record it under A4 with depth and propagation scope, but do not let it alone drive a red verdict — red requires an external dependency that cross-cuts the protocol or that the user did not opt into at deposit time. A failure mode that is "if the LRT you deposited is hacked, your principal in that LRT-backed market is impaired" is the underlying's autonomy story, not this protocol's; grade it on whether THIS protocol introduces additional dependencies on top.
- Sub-module enumeration is mandatory before grading. If the protocol ships distinct product lines or modules (e.g., a v2 core AMM plus a newer perps/funding-rate module, a lending pool plus a separate vault layer, an L1 core plus a cross-chain extension), enumerate each in findings and grade against the WORST module weighted by its share of TVS or its blast radius. A green core does not rescue an orange/red sub-module; conversely, a small red sub-module with capped TVS may bound the overall grade to orange. Name each module by its on-chain factory or router address. If you do not know whether a module exists, that is an unknowns[] entry, not silence. EXPLICIT TVS WEIGHTING: in the verdict, state each module's approximate share of total protocol TVS (use "~X%" if exact figures unavailable; check DeFiLlama or block-explorer balances on the module's main contract) and how that share informs the weighted grade. Format: "Module A holds ~X% of TVS (grade: <g>); Module B holds ~Y% (grade: <g>); weighted overall = <grade> because <reason>." If a red sub-module holds <5% of total TVS and is capped, the overall grade may be orange; if it holds >25%, the overall grade is red. Do not let qualitative reasoning substitute for the percentages — write the numbers.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- A1. External contract calls. Enumerate every external contract the core contracts call or read from (oracles, price feeds, AMM pools, lending pools, staking/deposit contracts, yield wrappers). For each, identify the address, the provider, and what user-facing function of this protocol would break or mis-price if that external contract paused, mis-reported, or behaved adversarially. Grep for "oracle", "aggregator", "getPrice", "latestAnswer", "chainlink", "pyth", "redstone" as a starting point. To verify an oracle is live and what it currently reports, hit https://defipunkd.com/api/contract/read?chainId=<id>&address=<oracle>&method=latestAnswer (or &method=latestRoundData, &method=getPrice, &method=description; use the BARE method name without parens) and cite the URL — the response includes blockNumber/blockHash and rawReturnData, which is stronger evidence than a docs page about which feed "should" be used.
- A2. Off-chain actor committees reporting INTO the protocol. Oracle committees, guardian multisigs, DAO-selected validator sets acting as protocol reporters, exit-bus signers, fraud-proof challengers. For each, record committee size, quorum, who picks the members, and what mis-reporting could do (mint, burn, finalize withdrawal, freeze). Distinguish this from governance admins (control slice). NOTE ON STAKING PROTOCOLS: validator slashing and node-operator misbehavior are properties of the base-chain substrate, NOT external dependencies, when the operator set is diversified enough that a coordinated failure caps at <5% principal loss. Count validator/operator risk under A2 ONLY if the operator set is small, non-diversified, or lacks bonding / slashing-insurance / diversification mitigations. A curated set of 30+ independent operators with documented diversification falls under the mitigated path; a 3-operator LST does not. Do not cite the protocol's own risk disclosure as evidence that operator failure = principal loss unless you also check the diversification and bond mitigations.
- A3. Bridge / cross-chain messaging dependencies. Only count bridges that carry material TVL or are required for a core user flow. For each, name the bridge operator (canonical L1↔L2, LayerZero, Wormhole, Axelar, custom multisig), the trust model (canonical, optimistic, light-client, guardian set), and what fraction of TVL or users ride on it. "wstETH exists on 15 chains" is not a finding unless material TVL sits there. Before listing any non-primary chain deployment as a dependency, verify it is still operational as of analysis_date — retired or sunset deployments (e.g., Lido-on-Terra, Lido-on-Solana) belong in unknowns[] or should be omitted, never cited as a current dependency.
- A4. Nested collateral / restaking chains. For restaking / LRT / receipt-of-receipt designs: record the depth of the collateral chain, every actor with slashing or freezing power at each level, and whether a failure N levels deep propagates to user principal here.
- A5. Fork lineage (silent check). If DeFiLlama's forkedFrom is non-empty, record it as one finding and move on. If empty, do NOT add a placeholder finding; it adds noise.
- A6. Fallback mechanisms and circuit breakers. What catches an external failure? Sanity-check contracts on oracle reports, rebase bounds, pause paths triggered by bad prices, second-opinion oracles, max-per-block throughput caps, withdrawal queues that absorb bad reports. Record which A1–A4 risks are mitigated by which fallback, and which are unmitigated. For EACH fallback you cite, state its activation status explicitly: (i) LIVE and enforcing on-chain today, (ii) DEPLOYED but not yet wired / activated (e.g., interface exists but the address is zero or the role is unassigned), or (iii) DOCUMENTED / PROPOSED only (forum post, LIP draft, audit pending). Only (i) counts as mitigation for the grade. A fallback in state (ii) or (iii) should be noted but must not reduce the risk in your steel-man or verdict. If you cannot determine activation status, add an unknowns[] entry rather than assume it is live.
- A7. Sequencer / L1-liveness dependency BEYOND the base-chain substrate. SCOPE — sequencer risk only counts here when the protocol IS its own L2/L3 appchain or app-rollup, where the sequencer is part of the protocol's own stack and a freeze is a protocol-level outage. A protocol permissionlessly deployed on a third-party L2 inherits that L2's sequencer as substrate, not an A7 dependency. Record the sequencer/DA trust model when A7 applies.
- A8. Keeper / relayer / off-chain bot liveness. Protocols that need permissionless-but-necessary off-chain actors (liquidation bots, auto-compounders, deposit relayers, intent solvers). Record whether the role is permissionless, what degrades if nobody runs it (yield paused, bad debt accumulates, positions go stale), and whether the failure mode is graceful or catastrophic.
- A9. Governance-mutable dependency surface. Can an admin or DAO action silently INTRODUCE a NEW EXTERNAL dependency — swap the oracle address to a different provider, register a new staking module that calls an untrusted contract, add a new bridge, route SY through a new external vault — without an exit window for users? Check the upgrade / router / module-registry contracts. Answer: which EXTERNAL dependencies are governance-mutable, who holds that power, and whether there is a timelock or exit window. SCOPE LIMIT — read carefully: A9 is about the *external dependency surface*, not the upgrade surface in general. "The proxyAdmin / EOA can upgrade the router implementation to arbitrary bytecode" is a CONTROL-slice finding (admin can rug), NOT an autonomy-A9 finding. A9 fires only when the upgrade specifically swaps out or adds a contract that THIS protocol calls or trusts (e.g., changing the oracle address from Chainlink to a malicious feed, registering a new SY adapter that points to a third-party vault, redirecting a bridge endpoint). If the only finding is "admin can change implementation," do not log it under A9 and do not let it drive the autonomy grade — note it under control instead. The autonomy-relevant version of the same upgrade key is "admin can swap [specific external address X] without timelock"; that requires identifying the specific external dependency that becomes mutable.

STEEL-MAN (per Hard Rule 13): write one-sentence strongest arguments for red, orange, and green using the A1–A9 findings.

IMPACTED TVS ESTIMATE: the headline MUST include a rough impacted-TVS figure — the fraction of protocol TVS that could be lost or frozen if the worst-unmitigated dependency you identified failed. Use "~X%" if exact numbers are unavailable, "<1%" for de minimis, "unclear" only if A1–A9 left the question genuinely open (in which case grade=unknown is usually correct). Do NOT substitute qualitative phrases like "significant" — give a number or bracket.

GRADE ANCHORS (mapped to DefiScan v1 stages):
- green = Stage 2 equivalent. Failure of any external dependency cannot cause loss of user principal or unclaimed yield. Either there are no material external dependencies, or every critical one has a documented fallback (A6) that keeps users whole. Governance cannot silently introduce new dependencies without an exit window (A9). Impacted TVS under any single-dependency failure: effectively 0.
- orange = Stage 1 equivalent. Failure of some external dependency can cause loss of unclaimed yield, or can materially change expected performance (pause withdrawals, freeze positions, degrade price quality), but cannot cause loss of principal. Committee-based oracles with sanity checks, canonical-only bridges, fallback paths that exist but are incomplete, or governance-mutable dependencies protected by a ≥7-day timelock. Impacted TVS is bounded and recoverable.
- red = Stage 0 equivalent. Failure of an external dependency CAN cause theft or loss of principal. Examples: single-provider oracle with no sanity check or fallback, material TVL on a non-canonical bridge with a guardian multisig, governance can hot-swap oracles or add staking modules with no timelock or exit window, unmitigated keeper-liveness dependency where positions become insolvent if bots stop. Impacted TVS is material.
- unknown = checklist incomplete after inspecting source + verified contracts. Prefer unknown over guessing when A1/A6 could not be reconstructed. RESERVE unknown for cases where the CORE ARCHITECTURE itself is unverifiable — not for cases where you merely cannot enumerate every per-market dependency in a multi-market protocol. If the core router/factory/oracle architecture is verifiable on-chain and you can determine whether the core requires external dependencies, grade the architecture even when an exhaustive per-market external-dependency census is infeasible. Acknowledge the per-market gap in unknowns[] but still issue a grade. Refusing to grade a multi-market protocol because you cannot list every SY/vault/market is over-use of unknown; grade the architecture and say so.

PROMPT-META CHECK (per Hard Rule 17): before finalizing, verify the verdict cites concrete contract addresses, docs, or code — not the rubric itself. If your verdict says "the protocol belongs to a category the rubric marks red", rewrite it with the A1–A9 finding that actually justifies the grade, or drop to grade=unknown.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "autonomy",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Open Access ✓ 3/3 models agree AI-only weak green — weak consensus margin Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-international
- protocol.name:              Polymarket International
- protocol.chains:            Polygon
- protocol.category:          Prediction Market
- protocol.website:           https://polymarket.com/?r=defillamareal
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               [
  {
    "chain": "Polygon",
    "address": "0xE111180000d2663C0091e4f400237545B87B996B",
    "role": "CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xe2222d279d744050d28e00520010520000310F59",
    "role": "Neg Risk CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296",
    "role": "Neg Risk Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0x4D97DCd97eC945f40cF65F87097ACe5EA0476045",
    "role": "Conditional Tokens (CTF)"
  },
  {
    "chain": "Polygon",
    "address": "0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB",
    "role": "pUSD CollateralToken (proxy)"
  },
  {
    "chain": "Polygon",
    "address": "0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f",
    "role": "pUSD CollateralToken (implementation)"
  },
  {
    "chain": "Polygon",
    "address": "0x93070a847efEf7F70739046A929D47a521F5B8ee",
    "role": "CollateralOnramp"
  },
  {
    "chain": "Polygon",
    "address": "0x2957922Eb93258b93368531d39fAcCA3B4dC5854",
    "role": "CollateralOfframp"
  },
  {
    "chain": "Polygon",
    "address": "0xebC2459Ec962869ca4c0bd1E06368272732BCb08",
    "role": "PermissionedRamp"
  },
  {
    "chain": "Polygon",
    "address": "0xAdA100Db00Ca00073811820692005400218FcE1f",
    "role": "CtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xadA2005600Dec949baf300f4C6120000bDB6eAab",
    "role": "NegRiskCtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xaacfeea03eb1561c4e67d661e40682bd20e3541b",
    "role": "Gnosis Safe Factory"
  },
  {
    "chain": "Polygon",
    "address": "0xaB45c5A4B0c941a2F231C04C3f49182e1A254052",
    "role": "Polymarket Proxy Factory"
  },
  {
    "chain": "Polygon",
    "address": "0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74",
    "role": "UMA Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0xCB1822859cEF82Cd2Eb4E6276C7916e692995130",
    "role": "UMA Optimistic Oracle"
  }
]

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
- https://defipunkd.com/address/137/0xE111180000d2663C0091e4f400237545B87B996B (CTF Exchange)
- https://defipunkd.com/address/137/0xe2222d279d744050d28e00520010520000310F59 (Neg Risk CTF Exchange)
- https://defipunkd.com/address/137/0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296 (Neg Risk Adapter)
- https://defipunkd.com/address/137/0x4D97DCd97eC945f40cF65F87097ACe5EA0476045 (Conditional Tokens (CTF))
- https://defipunkd.com/address/137/0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB (pUSD CollateralToken (proxy))
- https://defipunkd.com/address/137/0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f (pUSD CollateralToken (implementation))
- https://defipunkd.com/address/137/0x93070a847efEf7F70739046A929D47a521F5B8ee (CollateralOnramp)
- https://defipunkd.com/address/137/0x2957922Eb93258b93368531d39fAcCA3B4dC5854 (CollateralOfframp)
- https://defipunkd.com/address/137/0xebC2459Ec962869ca4c0bd1E06368272732BCb08 (PermissionedRamp)
- https://defipunkd.com/address/137/0xAdA100Db00Ca00073811820692005400218FcE1f (CtfCollateralAdapter)
- https://defipunkd.com/address/137/0xadA2005600Dec949baf300f4C6120000bDB6eAab (NegRiskCtfCollateralAdapter)
- https://defipunkd.com/address/137/0xaacfeea03eb1561c4e67d661e40682bd20e3541b (Gnosis Safe Factory)
- https://defipunkd.com/address/137/0xaB45c5A4B0c941a2F231C04C3f49182e1A254052 (Polymarket Proxy Factory)
- https://defipunkd.com/address/137/0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74 (UMA Adapter)
- https://defipunkd.com/address/137/0xCB1822859cEF82Cd2Eb4E6276C7916e692995130 (UMA Optimistic Oracle)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: OPEN-ACCESS

Evaluate who is allowed to use the protocol and whether any of that permission is granted off-chain.

Scope: this slice is about ADMISSION — who can enter, exit, or transact. Operator LIVENESS (what breaks if keepers/oracles go offline) is assessed in the dependencies slice and is out of scope for the grade here. You may note operator dependencies as context, but do not let "the protocol halts if operator X disappears" drive the access grade on its own; that belongs in dependencies. Source verification / contract verification on block explorers is assessed in the verifiability slice and is out of scope here — do NOT let "contract is unverified" drive the access grade.

Framing: the smart contracts are the access layer; frontends are UX. A permissionless contract is reachable by any client (SDK, third-party UI, aggregator, wallet integration). Frontend ToS, IP geo-blocking, and wallet screening are publisher policies on one specific client — they are reported as context but do NOT determine the grade. The grade hinges on (1) what the contract itself permits, and (2) whether the protocol is practically reachable without the official publisher's cooperation.

Meta-check before finalizing: if your verdict cites phrases from this prompt as evidence ("the protocol meets the 'credible alternatives' condition", "this fits the 'documented fallback' rule"), redo the verdict. The prompt describes the rubric; evidence must come from the protocol. A verdict should cite what the protocol does, not what the rubric says.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- A1. Whitelist / allowlist modifiers in user-facing entry points. Grep for "onlyWhitelisted", "onlyRole", "allowlist", "isAccredited", "isKYCed". Note which functions are gated and who can add/remove from the list.
- A2. Off-chain operators in the admission path: keepers, sequencers, privileged relayers, oracle posters whose approval is required to admit a user action (not just to keep the protocol live). For each, identify whether the role is held by a single operator, a permissioned committee, or is permissionless. Enumerate per user-facing function class (deposit vs withdraw-request vs claim-finalized vs transfer) which ones require operator approval to be admitted, and which ones admit users unconditionally. A function whose placement is unconditional but whose downstream settlement depends on an operator is an admission-permissionless function — flag the liveness dependency as context and defer its grading weight to the dependencies slice.
- A3. Frontend restrictions on the official interface — record as context, not as a grade lever. Distinguish:
    - A3-passive: boilerplate ToS clauses (sanctions attestation, restricted-territory self-certification, VPN-circumvention prohibition, "comply with applicable law" eligibility, age of majority).
    - A3-active: runtime enforcement — IP-based geo-blocking, wallet-address screening against a sanctions oracle (Chainalysis, TRM, Elliptic), KYC wall, rendering-blocking jurisdiction banner.
  Record findings under the correct tier. Quote ToS text or banner text in evidence[].shows. These findings populate the headline and rationale but do NOT move the grade by themselves; the grade is set by A1, A2, and the A3b path check below.
- A3b. Independent access paths (the operative grade input). Enumerate paths that do not require the official publisher's cooperation:
    - Published SDK / library / CLI for direct contract interaction.
    - Third-party frontends operated by separate legal entities.
    - Wallet-integrated access (MetaMask Swaps, Safe apps, etc.).
    - DEX / lending / yield aggregators that route through the contracts.
  Record at least one concrete link per path that exists. The protocol does NOT have to self-document these — the test is existence, not UX cost. An A3b-i redistribution of the official UI bound by the same ToS does NOT count as an independent path.
- A4. Sanctions / compliance tooling at the contract level: does the protocol check addresses against OFAC lists or similar on-chain blocklists in the contract itself? (Frontend-only screening belongs in A3.)
- A5. Differentiate read access vs write access: many protocols are read-permissionless (anyone can view state) but write-gated (only certain addresses can deposit/borrow). Record both.
- A6. ToS / Legal links: locate them on the website and produce a VERBATIM quote of any jurisdictional, sanctions, or eligibility clause in evidence[].shows. If you cannot extract the clause text verbatim (SPA render failure, paywall, dead link, etc.), do NOT paraphrase or infer from general knowledge — record the ToS URL in unknowns[] with the reason extraction failed. Assertions about ToS content without a verbatim quote will be downweighted by reviewers.

Then write the steel-man section per Hard Rule 11.

Grade rules (admission-focused; liveness concerns belong in dependencies; source verification belongs in verifiability):
- green   = no contract-level whitelist/KYC on user entry/exit; no operator approval required to admit a user action; AND at least one independent A3b path exists (published SDK, third-party frontend, wallet integration, or aggregator routing). Frontend ToS posture and A3-active enforcement on the official UI do NOT block green when contracts are permissionless and an independent path exists — they are reported as context.
- orange  = contracts admit users unconditionally, BUT the protocol is operationally captured by the official publisher: no published SDK, no third-party frontend, no wallet integration, no aggregator routing. The contract is theoretically open but practically reachable only through the official UI. Also applies when admission requires approval from a permissioned committee that is governance-managed with a documented replacement procedure.
- red     = contract-level whitelist / KYC on user entry/exit, OR admission of a core user action requires approval from a single privileged operator or a small committee with no documented replacement procedure, OR enforces an on-chain blocklist updatable by a single party.
- unknown = checklist incomplete after checking the sources above.

Default-grade guidance: when contracts are fully permissionless AND any A3b independent path exists, the default grade is green regardless of frontend ToS or A3-active enforcement on the official UI. Frontend geo-blocking, sanctions-oracle wallet screening, and ToS sanctions clauses are publisher policies on one client and are reported in findings/headline as context, not as grade levers. To grade orange on operational-capture grounds, the auditor must affirmatively show that ALL independent paths are absent or also gated.

Guideline on committees: where admission depends on a multi-operator committee, the relevant axes are (a) set size, (b) whether replacement/rotation is governed on-chain, (c) whether the replacement procedure is publicly documented. A large set with on-chain governance replacement should not be graded as a single-party operator even if rotation is not instantaneous. A small set with informal replacement should be treated as a single-party operator.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "open-access",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Audit all 5 dimensions · one prompt Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-international
- protocol.name:              Polymarket International
- protocol.chains:            Polygon
- protocol.category:          Prediction Market
- protocol.website:           https://polymarket.com/?r=defillamareal
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               [
  {
    "chain": "Polygon",
    "address": "0xE111180000d2663C0091e4f400237545B87B996B",
    "role": "CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xe2222d279d744050d28e00520010520000310F59",
    "role": "Neg Risk CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296",
    "role": "Neg Risk Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0x4D97DCd97eC945f40cF65F87097ACe5EA0476045",
    "role": "Conditional Tokens (CTF)"
  },
  {
    "chain": "Polygon",
    "address": "0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB",
    "role": "pUSD CollateralToken (proxy)"
  },
  {
    "chain": "Polygon",
    "address": "0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f",
    "role": "pUSD CollateralToken (implementation)"
  },
  {
    "chain": "Polygon",
    "address": "0x93070a847efEf7F70739046A929D47a521F5B8ee",
    "role": "CollateralOnramp"
  },
  {
    "chain": "Polygon",
    "address": "0x2957922Eb93258b93368531d39fAcCA3B4dC5854",
    "role": "CollateralOfframp"
  },
  {
    "chain": "Polygon",
    "address": "0xebC2459Ec962869ca4c0bd1E06368272732BCb08",
    "role": "PermissionedRamp"
  },
  {
    "chain": "Polygon",
    "address": "0xAdA100Db00Ca00073811820692005400218FcE1f",
    "role": "CtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xadA2005600Dec949baf300f4C6120000bDB6eAab",
    "role": "NegRiskCtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xaacfeea03eb1561c4e67d661e40682bd20e3541b",
    "role": "Gnosis Safe Factory"
  },
  {
    "chain": "Polygon",
    "address": "0xaB45c5A4B0c941a2F231C04C3f49182e1A254052",
    "role": "Polymarket Proxy Factory"
  },
  {
    "chain": "Polygon",
    "address": "0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74",
    "role": "UMA Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0xCB1822859cEF82Cd2Eb4E6276C7916e692995130",
    "role": "UMA Optimistic Oracle"
  }
]

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
- https://defipunkd.com/address/137/0xE111180000d2663C0091e4f400237545B87B996B (CTF Exchange)
- https://defipunkd.com/address/137/0xe2222d279d744050d28e00520010520000310F59 (Neg Risk CTF Exchange)
- https://defipunkd.com/address/137/0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296 (Neg Risk Adapter)
- https://defipunkd.com/address/137/0x4D97DCd97eC945f40cF65F87097ACe5EA0476045 (Conditional Tokens (CTF))
- https://defipunkd.com/address/137/0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB (pUSD CollateralToken (proxy))
- https://defipunkd.com/address/137/0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f (pUSD CollateralToken (implementation))
- https://defipunkd.com/address/137/0x93070a847efEf7F70739046A929D47a521F5B8ee (CollateralOnramp)
- https://defipunkd.com/address/137/0x2957922Eb93258b93368531d39fAcCA3B4dC5854 (CollateralOfframp)
- https://defipunkd.com/address/137/0xebC2459Ec962869ca4c0bd1E06368272732BCb08 (PermissionedRamp)
- https://defipunkd.com/address/137/0xAdA100Db00Ca00073811820692005400218FcE1f (CtfCollateralAdapter)
- https://defipunkd.com/address/137/0xadA2005600Dec949baf300f4C6120000bDB6eAab (NegRiskCtfCollateralAdapter)
- https://defipunkd.com/address/137/0xaacfeea03eb1561c4e67d661e40682bd20e3541b (Gnosis Safe Factory)
- https://defipunkd.com/address/137/0xaB45c5A4B0c941a2F231C04C3f49182e1A254052 (Polymarket Proxy Factory)
- https://defipunkd.com/address/137/0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74 (UMA Adapter)
- https://defipunkd.com/address/137/0xCB1822859cEF82Cd2Eb4E6276C7916e692995130 (UMA Optimistic Oracle)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: CONTROL

Evaluate who can change the protocol's rules, how fast, and how broadly.

(Step 0 capability probe and the off-chain-only fallback live in the preamble — those rules apply here.)

### MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[])

- **C1.** For each address you assess: who is the contract owner / admin / pendingAdmin / governor — read these via the block explorer's "Read Contract" tab OR `https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=owner` (BARE method names: `&method=owner`, `&method=admin`, `&method=pendingOwner`, `&method=governor`). For Safes use `/api/safe/owners?chainId=<id>&address=0x...`. When a protocol has multiple major versions deployed (v2/v3/v4), perform C1 reads on the NEWEST deployment separately — newer deployments often have weaker control surfaces than the legacy core.
- **C2.** Upgrade mechanism: transparent proxy / UUPS / Beacon / Diamond / immutable. Identify the proxy admin address. Check upgradeability of GOVERNANCE contracts too — a Governor / Aragon Voting / OZ Governor is often itself a proxy whose admin is the Timelock. Asymmetry: when fund-holding cores are immutable AND governance has no admin path that reaches them, an upgradable Governor/Timelock is T3-only and must NOT drag the verdict below green on that basis alone (see grade rules and the "immutable cores" caveat). Only call upgradability "mixed" if you can name a concrete function on the upgradable surface that reaches T1 or T2 on user funds.
- **C3.** EXECUTION PATH (enumerate every stage, in order, with delays in seconds). The operative path is usually a chain (voting → scheduler → timelock → executor; or governor → queue → execute; or Aragon Voting → DualGovernance → EmergencyProtectedTimelock → AdminExecutor). For each stage, record (a) the contract address, (b) the delay constant name + value in seconds, (c) the URL you read it from (block-explorer Read Contract OR `/api/contract/read?...&method=MIN_DELAY&block=<n>`). Do NOT stop at the first timelock-shaped contract — if its admin is itself called by another contract, keep walking. The grading delay is the SUM OF DELAYS ON THE UNCONTESTED FAST PATH (shortest time a proposal with no opposition can go from submission to executable). Dynamic / contested extensions (veto signaling, rage quit, escrow delay) are modifiers, not the basis — note them separately.
- **C4.** Enumerate EVERY multisig with reachable control — main proxy admin, emergency activation, emergency execution, reseal / pause, gate-seal committees, tiebreaker, per-module admins. For each Safe, fetch threshold + owners + version via `/api/safe/owners?chainId=<id>&address=0x...` (response includes raw eth_call data, so the URL is citable evidence). Enumerate ops/council/incentives multisigs even when off the upgrade path — record their scope so a reader can see they are NOT on the upgrade path. For each: (a) address, (b) threshold / total signers, (c) signer identities classified as insider (team, paid auditors under ongoing engagement, mandated service providers) vs non-insider (independent community members, unaffiliated researchers), (d) the specific power held (upgrade, pause, parameter, etc.).
- **C5.** On-chain governance: Governor / GovernorBravo / OZ Governor / Aragon Voting with token-weighted voting? Record proposal threshold, voting period, quorum, and the timelock delay between queue and execute. Every numeric constant must come from a Read Contract call you can link to, or be in unknowns[] with the C-code. If votingDelay / votingPeriod are denominated in BLOCKS, convert to seconds at the chain's CURRENT block time (Ethereum mainnet ≈ 12s post-Merge, not the 15s in older Compound/Bravo deployments) — cite both block count and converted seconds.
- **C6.** EMERGENCY POWERS: separate emergency-pause / guardian role with a different time cap or different actor than the main upgrade authority? Record it explicitly.
- **C7.** POWER TIER (blast radius). For each privileged path in C3–C6, classify the WORST thing that path can do, choosing the highest applicable tier. Cite the specific function name and any on-chain bound — tier claims without a named function are unsupported.
    - **T1 — FUND-CRITICAL**: replace implementation of contracts holding user funds; change AMM math / accounting / collateral logic; mint unbacked debt or shares; pause withdrawals; drain user-fund treasury; change oracle to attacker-controlled source; replace upgrade admin with EOA.
    - **T2 — ECONOMICALLY MATERIAL**: change fee parameters within bounded ranges; redirect protocol fees; add/remove markets / collateral types; bounded inflation or token mint within hard-capped schedule; spend protocol-owned (non-user) treasury.
    - **T3 — GOVERNANCE-INTERNAL**: change voting rules, quorum, voting period, proposal threshold; upgrade the Governor itself; rotate Timelock admin; mint governance tokens within a capped annual schedule.
    - **T4 — OPERATIONAL**: incentives distribution, grants, ENS / frontend canonicalization, deployment coordination, periphery router deprecation.
  The grade is set by the HIGHEST tier reachable on the uncontested fast path, not the median. State the tier and the binding function in the verdict.

### Read Contract discipline (applies to C3, C4, C5)

Every numeric constant cited (timelock delays, voting periods, multisig thresholds, quorum percentages) must come from EITHER (a) a block-explorer Read Contract URL, OR (b) a DeFiPunkd `/api/contract/read` or `/api/safe/owners` URL (preferred with `&block=<n>` for content-addressed evidence), OR (c) an unknowns[] entry with the C-code. Docs / blog posts are corroboration only — they cannot be the sole citation for a value that is also readable on-chain.

### Off-chain-only substitute hierarchy (when grading_basis="off-chain-only" — see preamble Rule 16)

When on-chain reads were genuinely unreachable this run, eligible off-chain substitutes in priority order:
1. Linked audit PDFs (admin roles, multisig members, timelock delays usually enumerated).
2. Governance forum posts that quote constants from a successful on-chain proposal (cite post URL + linked execution-tx URL).
3. Official protocol docs pages with named addresses and roles (must be on a domain owned by the protocol).
4. GitHub README / SECURITY.md / governance/*.md at a pinned commit SHA.

Forbidden substitutes: third-party blog posts, X / Twitter threads, search-result snippets, model memory. Required degradation: any C-code citing a numeric constant from docs/forum/audit prose ONLY must also carry an `unknowns[]` entry with `-offchain` suffix noting "value not re-read on-chain in this run; corroboration only".

### Grade rules (apply the timelock bar conditional on the highest C7 tier reachable on the fast path)

Security Council standard (used below): a multisig qualifies as "Security Council" only if ALL of: ≥7 signers, ≥51% threshold, ≥50% non-insider signers, every signer publicly announced. Failing any criterion = NOT a Security Council, regardless of signer reputation.

- **green**: highest reachable tier is T3 or T4 regardless of timelock; OR T2 reachable with uncontested-fast-path delay ≥7 days; OR T1 reachable only via immutable contracts (T1 is unreachable); OR T1 reachable with uncontested-fast-path delay ≥7 days combined with a Security Council multisig; OR T1 reachable with uncontested-fast-path delay ≥7 days through active on-chain governance with broad token distribution.
- **orange**: T2 reachable with uncontested-fast-path delay >0 but <7 days; OR T1 reachable with uncontested-fast-path delay >0 but <7 days; OR a multisig failing one or more Security Council criteria sits on a T1/T2 path; OR unclear upgrade authority on a T1/T2 path; OR governance with very short timelock or low quorum on a T1/T2 path.
- **red**: T1 reachable with no timelock by a single EOA or 2-of-3 multisig; OR a T1 upgrade admin that is not a smart contract you can audit.
- **unknown**: completed the checklist but still cannot determine the upgrade authority OR cannot classify the highest tier reachable on the main contracts.

Tiering caveats:
- "Bounded" must be enforced ON-CHAIN to count as T2. A function that sets fees with no upper-bound check is T1 — cite the bound check.
- Recurring T2 economic extraction (e.g. fee redirect with no rate limit) approaches T1 over time. A single proposal that can permanently redirect all future revenue is T1.
- T3 assumes the governance contract cannot itself authorize a T1/T2 action without going through the same timelock. If governance can self-upgrade to bypass the timelock, T3 collapses into T1.
- Do not downgrade tier by hand-waving ("realistically governance would never…"). Tier on what the contract permits, not what feels likely.

Notes:
- **Dynamic / dual-governance timelocks** (Lido, Compound escrow veto): the rubric grades on the uncontested path because that is the path most upgrades take. A dynamic extension that fires only under stake-weighted opposition is a real protection — name it in the green steel-man, but it does not lift an orange fast path into green; state the tension in the verdict.
- **Immutable cores with upgradable governance** (Uniswap-style): if fund-holding contracts are immutable and have no admin-reachable function moving / freezing / re-routing user funds, the highest reachable tier on the upgrade path is T3 — green regardless of timelock. Don't grade this orange just because the Governor is a proxy — that's a C2 fact, not a downgrade. Downgrade only applies if you can cite a concrete function on the upgradable surface that reaches T1 or T2 (privileged hook, upgradable factory controlling fund-routing, fee-switch redirecting protocol revenue without bound).
- **The 7-day bar** reflects the exit-window standard — users need notice after a queued upgrade to withdraw if they disagree. The ability-to-exit slice grades the exit side; this slice grades the delay side; both must hold for users to actually benefit from the delay.

---

### Slice: ABILITY-TO-EXIT

Evaluate whether users can withdraw their funds on their own terms, even under adversarial admin conditions.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- E1. Enumerate every user-facing exit function in the main contracts: withdraw, redeem, burn, requestWithdrawal, claim, exit, etc. List them by name. Do NOT treat the contract as a monolith.
- E2. For EACH exit function in E1: identify its access modifiers and any pause guards (e.g. _checkResumed, whenNotPaused, onlyRole). Functions that gate REQUEST PLACEMENT often differ from functions that CLAIM FINALIZED FUNDS — check both separately.
- E3. For each pause guard: identify the role holder (which address holds PAUSE_ROLE / GUARDIAN / etc.) and the maximum pause duration. Specifically check whether PAUSE_INFINITELY (or equivalent uncapped pause) is callable, and which actor can call it (single multisig vs governance vote). For role-holder reads use https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=hasRole&args=0x...,0x... or &method=getRoleAdmin&args=0x.... For "is currently paused" checks use &method=paused or &method=isPaused&args=<resume-code>. Use the BARE method name (no parens). Cite the URL with &block=<n> in evidence[].
- E4. EMERGENCY vs GOVERNANCE pause distinction: many protocols have a fast-acting emergency pause capped at N days and a slow governance pause that can be indefinite. Record both paths separately if present, with their time caps and actor classes.
- E5. Queued redemption: documented maximum queue duration, daily withdrawal caps, whether the queue itself is pausable.
- E6. Forced-exit / escape-hatch / permissionless emergency-exit mechanism for adversarial-admin scenarios.
- E7. Frontend dependency: confirm exit functions are directly callable on-chain (e.g. via Etherscan write tab or a generic wallet) without the project's frontend.

Then write the steel-man section per Hard Rule 11. Common red-vs-orange tension on this slice: indefinite pause exists (suggests red) BUT the realistic emergency path is time-capped AND claims of already-finalized exits are not pause-gated (suggests orange). Resolve this by stating who can do what for how long, not by stopping at the worst-case sentence.

Grade rules:
- green   = permissionless exit; pause is either absent, narrowly scoped to clearly-described emergencies with auto-expiry, or capped at ≤7 days; no frontend dependency for exit; claims of already-finalized exits are not pause-gated under any path.
- orange  = pausable with broad scope OR indefinite pause is reachable only through governance vote (not unilateral admin action), OR queued redemption with documented max > 7 days, OR claims-of-finalized are exempt but new-request placement can be paused indefinitely by governance.
- red     = exit requires admin signature, OR ANY actor (including governance) can pause CLAIMS of finalized exits indefinitely, OR there is no on-chain exit function at all (purely custodial), OR pause is held by a single EOA / 2-of-3 multisig with no time cap.
- unknown = checklist incomplete after checking the sources above.

---

### Slice: AUTONOMY

Evaluate this protocol's autonomy: can a failure of anything outside its own contracts cause theft or loss of user principal, loss of unclaimed yield, or materially change the protocol's expected performance? "Autonomy" is not "has zero external touchpoints" — it is "external failures are either survivable or recoverable without user loss". This slice adapts DefiScan v1's Autonomy dimension; dependencies are one of several criteria, not the whole frame.

GUARDRAILS (read before grading):
- Category alone (Liquid Staking, Bridge, RWA Lending, Restaking, …) does NOT force a grade. A category is a hint about where to look; the grade must come from the concrete A1–A9 findings below.
- Base-chain consensus (Ethereum PoS, the chain's validator set, the canonical Deposit Contract at 0x00000000219ab540356cBB839Cbe05303d7705Fa) is the SUBSTRATE, not a dependency, for any protocol deployed on that chain. Do not list "depends on Ethereum" as a finding.
- Oracles or other integrations used by DOWNSTREAM protocols that happen to read this protocol's token (e.g. Chainlink stETH/USD consumed by Aave) are NOT this protocol's dependencies. Count only what THIS protocol's contracts call or trust on-chain. If a feed or contract appears in the protocol's docs only as reference material for third-party integrators, EXCLUDE IT ENTIRELY — do not log it as a finding even with a "peripheral" or "referenced only" caveat.
- "Upgradeable admin can change things" belongs to the CONTROL slice; only count it here when the upgrade surface lets governance silently swap an external dependency (see A9).
- Underlying-asset risk in opt-in, isolated markets is NOT autonomy-red on its own. When a protocol wraps third-party yield-bearing assets (LSTs, LRTs, ERC-4626 vaults, lending receipts, restaked tokens) into per-market silos that users explicitly choose, a failure of one underlying does NOT propagate to other markets and is risk the user opted into per-market. Record it under A4 with depth and propagation scope, but do not let it alone drive a red verdict — red requires an external dependency that cross-cuts the protocol or that the user did not opt into at deposit time. A failure mode that is "if the LRT you deposited is hacked, your principal in that LRT-backed market is impaired" is the underlying's autonomy story, not this protocol's; grade it on whether THIS protocol introduces additional dependencies on top.
- Sub-module enumeration is mandatory before grading. If the protocol ships distinct product lines or modules (e.g., a v2 core AMM plus a newer perps/funding-rate module, a lending pool plus a separate vault layer, an L1 core plus a cross-chain extension), enumerate each in findings and grade against the WORST module weighted by its share of TVS or its blast radius. A green core does not rescue an orange/red sub-module; conversely, a small red sub-module with capped TVS may bound the overall grade to orange. Name each module by its on-chain factory or router address. If you do not know whether a module exists, that is an unknowns[] entry, not silence. EXPLICIT TVS WEIGHTING: in the verdict, state each module's approximate share of total protocol TVS (use "~X%" if exact figures unavailable; check DeFiLlama or block-explorer balances on the module's main contract) and how that share informs the weighted grade. Format: "Module A holds ~X% of TVS (grade: <g>); Module B holds ~Y% (grade: <g>); weighted overall = <grade> because <reason>." If a red sub-module holds <5% of total TVS and is capped, the overall grade may be orange; if it holds >25%, the overall grade is red. Do not let qualitative reasoning substitute for the percentages — write the numbers.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- A1. External contract calls. Enumerate every external contract the core contracts call or read from (oracles, price feeds, AMM pools, lending pools, staking/deposit contracts, yield wrappers). For each, identify the address, the provider, and what user-facing function of this protocol would break or mis-price if that external contract paused, mis-reported, or behaved adversarially. Grep for "oracle", "aggregator", "getPrice", "latestAnswer", "chainlink", "pyth", "redstone" as a starting point. To verify an oracle is live and what it currently reports, hit https://defipunkd.com/api/contract/read?chainId=<id>&address=<oracle>&method=latestAnswer (or &method=latestRoundData, &method=getPrice, &method=description; use the BARE method name without parens) and cite the URL — the response includes blockNumber/blockHash and rawReturnData, which is stronger evidence than a docs page about which feed "should" be used.
- A2. Off-chain actor committees reporting INTO the protocol. Oracle committees, guardian multisigs, DAO-selected validator sets acting as protocol reporters, exit-bus signers, fraud-proof challengers. For each, record committee size, quorum, who picks the members, and what mis-reporting could do (mint, burn, finalize withdrawal, freeze). Distinguish this from governance admins (control slice). NOTE ON STAKING PROTOCOLS: validator slashing and node-operator misbehavior are properties of the base-chain substrate, NOT external dependencies, when the operator set is diversified enough that a coordinated failure caps at <5% principal loss. Count validator/operator risk under A2 ONLY if the operator set is small, non-diversified, or lacks bonding / slashing-insurance / diversification mitigations. A curated set of 30+ independent operators with documented diversification falls under the mitigated path; a 3-operator LST does not. Do not cite the protocol's own risk disclosure as evidence that operator failure = principal loss unless you also check the diversification and bond mitigations.
- A3. Bridge / cross-chain messaging dependencies. Only count bridges that carry material TVL or are required for a core user flow. For each, name the bridge operator (canonical L1↔L2, LayerZero, Wormhole, Axelar, custom multisig), the trust model (canonical, optimistic, light-client, guardian set), and what fraction of TVL or users ride on it. "wstETH exists on 15 chains" is not a finding unless material TVL sits there. Before listing any non-primary chain deployment as a dependency, verify it is still operational as of analysis_date — retired or sunset deployments (e.g., Lido-on-Terra, Lido-on-Solana) belong in unknowns[] or should be omitted, never cited as a current dependency.
- A4. Nested collateral / restaking chains. For restaking / LRT / receipt-of-receipt designs: record the depth of the collateral chain, every actor with slashing or freezing power at each level, and whether a failure N levels deep propagates to user principal here.
- A5. Fork lineage (silent check). If DeFiLlama's forkedFrom is non-empty, record it as one finding and move on. If empty, do NOT add a placeholder finding; it adds noise.
- A6. Fallback mechanisms and circuit breakers. What catches an external failure? Sanity-check contracts on oracle reports, rebase bounds, pause paths triggered by bad prices, second-opinion oracles, max-per-block throughput caps, withdrawal queues that absorb bad reports. Record which A1–A4 risks are mitigated by which fallback, and which are unmitigated. For EACH fallback you cite, state its activation status explicitly: (i) LIVE and enforcing on-chain today, (ii) DEPLOYED but not yet wired / activated (e.g., interface exists but the address is zero or the role is unassigned), or (iii) DOCUMENTED / PROPOSED only (forum post, LIP draft, audit pending). Only (i) counts as mitigation for the grade. A fallback in state (ii) or (iii) should be noted but must not reduce the risk in your steel-man or verdict. If you cannot determine activation status, add an unknowns[] entry rather than assume it is live.
- A7. Sequencer / L1-liveness dependency BEYOND the base-chain substrate. SCOPE — sequencer risk only counts here when the protocol IS its own L2/L3 appchain or app-rollup, where the sequencer is part of the protocol's own stack and a freeze is a protocol-level outage. A protocol permissionlessly deployed on a third-party L2 inherits that L2's sequencer as substrate, not an A7 dependency. Record the sequencer/DA trust model when A7 applies.
- A8. Keeper / relayer / off-chain bot liveness. Protocols that need permissionless-but-necessary off-chain actors (liquidation bots, auto-compounders, deposit relayers, intent solvers). Record whether the role is permissionless, what degrades if nobody runs it (yield paused, bad debt accumulates, positions go stale), and whether the failure mode is graceful or catastrophic.
- A9. Governance-mutable dependency surface. Can an admin or DAO action silently INTRODUCE a NEW EXTERNAL dependency — swap the oracle address to a different provider, register a new staking module that calls an untrusted contract, add a new bridge, route SY through a new external vault — without an exit window for users? Check the upgrade / router / module-registry contracts. Answer: which EXTERNAL dependencies are governance-mutable, who holds that power, and whether there is a timelock or exit window. SCOPE LIMIT — read carefully: A9 is about the *external dependency surface*, not the upgrade surface in general. "The proxyAdmin / EOA can upgrade the router implementation to arbitrary bytecode" is a CONTROL-slice finding (admin can rug), NOT an autonomy-A9 finding. A9 fires only when the upgrade specifically swaps out or adds a contract that THIS protocol calls or trusts (e.g., changing the oracle address from Chainlink to a malicious feed, registering a new SY adapter that points to a third-party vault, redirecting a bridge endpoint). If the only finding is "admin can change implementation," do not log it under A9 and do not let it drive the autonomy grade — note it under control instead. The autonomy-relevant version of the same upgrade key is "admin can swap [specific external address X] without timelock"; that requires identifying the specific external dependency that becomes mutable.

STEEL-MAN (per Hard Rule 13): write one-sentence strongest arguments for red, orange, and green using the A1–A9 findings.

IMPACTED TVS ESTIMATE: the headline MUST include a rough impacted-TVS figure — the fraction of protocol TVS that could be lost or frozen if the worst-unmitigated dependency you identified failed. Use "~X%" if exact numbers are unavailable, "<1%" for de minimis, "unclear" only if A1–A9 left the question genuinely open (in which case grade=unknown is usually correct). Do NOT substitute qualitative phrases like "significant" — give a number or bracket.

GRADE ANCHORS (mapped to DefiScan v1 stages):
- green = Stage 2 equivalent. Failure of any external dependency cannot cause loss of user principal or unclaimed yield. Either there are no material external dependencies, or every critical one has a documented fallback (A6) that keeps users whole. Governance cannot silently introduce new dependencies without an exit window (A9). Impacted TVS under any single-dependency failure: effectively 0.
- orange = Stage 1 equivalent. Failure of some external dependency can cause loss of unclaimed yield, or can materially change expected performance (pause withdrawals, freeze positions, degrade price quality), but cannot cause loss of principal. Committee-based oracles with sanity checks, canonical-only bridges, fallback paths that exist but are incomplete, or governance-mutable dependencies protected by a ≥7-day timelock. Impacted TVS is bounded and recoverable.
- red = Stage 0 equivalent. Failure of an external dependency CAN cause theft or loss of principal. Examples: single-provider oracle with no sanity check or fallback, material TVL on a non-canonical bridge with a guardian multisig, governance can hot-swap oracles or add staking modules with no timelock or exit window, unmitigated keeper-liveness dependency where positions become insolvent if bots stop. Impacted TVS is material.
- unknown = checklist incomplete after inspecting source + verified contracts. Prefer unknown over guessing when A1/A6 could not be reconstructed. RESERVE unknown for cases where the CORE ARCHITECTURE itself is unverifiable — not for cases where you merely cannot enumerate every per-market dependency in a multi-market protocol. If the core router/factory/oracle architecture is verifiable on-chain and you can determine whether the core requires external dependencies, grade the architecture even when an exhaustive per-market external-dependency census is infeasible. Acknowledge the per-market gap in unknowns[] but still issue a grade. Refusing to grade a multi-market protocol because you cannot list every SY/vault/market is over-use of unknown; grade the architecture and say so.

PROMPT-META CHECK (per Hard Rule 17): before finalizing, verify the verdict cites concrete contract addresses, docs, or code — not the rubric itself. If your verdict says "the protocol belongs to a category the rubric marks red", rewrite it with the A1–A9 finding that actually justifies the grade, or drop to grade=unknown.

---

### Slice: OPEN-ACCESS

Evaluate who is allowed to use the protocol and whether any of that permission is granted off-chain.

Scope: this slice is about ADMISSION — who can enter, exit, or transact. Operator LIVENESS (what breaks if keepers/oracles go offline) is assessed in the dependencies slice and is out of scope for the grade here. You may note operator dependencies as context, but do not let "the protocol halts if operator X disappears" drive the access grade on its own; that belongs in dependencies. Source verification / contract verification on block explorers is assessed in the verifiability slice and is out of scope here — do NOT let "contract is unverified" drive the access grade.

Framing: the smart contracts are the access layer; frontends are UX. A permissionless contract is reachable by any client (SDK, third-party UI, aggregator, wallet integration). Frontend ToS, IP geo-blocking, and wallet screening are publisher policies on one specific client — they are reported as context but do NOT determine the grade. The grade hinges on (1) what the contract itself permits, and (2) whether the protocol is practically reachable without the official publisher's cooperation.

Meta-check before finalizing: if your verdict cites phrases from this prompt as evidence ("the protocol meets the 'credible alternatives' condition", "this fits the 'documented fallback' rule"), redo the verdict. The prompt describes the rubric; evidence must come from the protocol. A verdict should cite what the protocol does, not what the rubric says.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- A1. Whitelist / allowlist modifiers in user-facing entry points. Grep for "onlyWhitelisted", "onlyRole", "allowlist", "isAccredited", "isKYCed". Note which functions are gated and who can add/remove from the list.
- A2. Off-chain operators in the admission path: keepers, sequencers, privileged relayers, oracle posters whose approval is required to admit a user action (not just to keep the protocol live). For each, identify whether the role is held by a single operator, a permissioned committee, or is permissionless. Enumerate per user-facing function class (deposit vs withdraw-request vs claim-finalized vs transfer) which ones require operator approval to be admitted, and which ones admit users unconditionally. A function whose placement is unconditional but whose downstream settlement depends on an operator is an admission-permissionless function — flag the liveness dependency as context and defer its grading weight to the dependencies slice.
- A3. Frontend restrictions on the official interface — record as context, not as a grade lever. Distinguish:
    - A3-passive: boilerplate ToS clauses (sanctions attestation, restricted-territory self-certification, VPN-circumvention prohibition, "comply with applicable law" eligibility, age of majority).
    - A3-active: runtime enforcement — IP-based geo-blocking, wallet-address screening against a sanctions oracle (Chainalysis, TRM, Elliptic), KYC wall, rendering-blocking jurisdiction banner.
  Record findings under the correct tier. Quote ToS text or banner text in evidence[].shows. These findings populate the headline and rationale but do NOT move the grade by themselves; the grade is set by A1, A2, and the A3b path check below.
- A3b. Independent access paths (the operative grade input). Enumerate paths that do not require the official publisher's cooperation:
    - Published SDK / library / CLI for direct contract interaction.
    - Third-party frontends operated by separate legal entities.
    - Wallet-integrated access (MetaMask Swaps, Safe apps, etc.).
    - DEX / lending / yield aggregators that route through the contracts.
  Record at least one concrete link per path that exists. The protocol does NOT have to self-document these — the test is existence, not UX cost. An A3b-i redistribution of the official UI bound by the same ToS does NOT count as an independent path.
- A4. Sanctions / compliance tooling at the contract level: does the protocol check addresses against OFAC lists or similar on-chain blocklists in the contract itself? (Frontend-only screening belongs in A3.)
- A5. Differentiate read access vs write access: many protocols are read-permissionless (anyone can view state) but write-gated (only certain addresses can deposit/borrow). Record both.
- A6. ToS / Legal links: locate them on the website and produce a VERBATIM quote of any jurisdictional, sanctions, or eligibility clause in evidence[].shows. If you cannot extract the clause text verbatim (SPA render failure, paywall, dead link, etc.), do NOT paraphrase or infer from general knowledge — record the ToS URL in unknowns[] with the reason extraction failed. Assertions about ToS content without a verbatim quote will be downweighted by reviewers.

Then write the steel-man section per Hard Rule 11.

Grade rules (admission-focused; liveness concerns belong in dependencies; source verification belongs in verifiability):
- green   = no contract-level whitelist/KYC on user entry/exit; no operator approval required to admit a user action; AND at least one independent A3b path exists (published SDK, third-party frontend, wallet integration, or aggregator routing). Frontend ToS posture and A3-active enforcement on the official UI do NOT block green when contracts are permissionless and an independent path exists — they are reported as context.
- orange  = contracts admit users unconditionally, BUT the protocol is operationally captured by the official publisher: no published SDK, no third-party frontend, no wallet integration, no aggregator routing. The contract is theoretically open but practically reachable only through the official UI. Also applies when admission requires approval from a permissioned committee that is governance-managed with a documented replacement procedure.
- red     = contract-level whitelist / KYC on user entry/exit, OR admission of a core user action requires approval from a single privileged operator or a small committee with no documented replacement procedure, OR enforces an on-chain blocklist updatable by a single party.
- unknown = checklist incomplete after checking the sources above.

Default-grade guidance: when contracts are fully permissionless AND any A3b independent path exists, the default grade is green regardless of frontend ToS or A3-active enforcement on the official UI. Frontend geo-blocking, sanctions-oracle wallet screening, and ToS sanctions clauses are publisher policies on one client and are reported in findings/headline as context, not as grade levers. To grade orange on operational-capture grounds, the auditor must affirmatively show that ALL independent paths are absent or also gated.

Guideline on committees: where admission depends on a multi-operator committee, the relevant axes are (a) set size, (b) whether replacement/rotation is governed on-chain, (c) whether the replacement procedure is publicly documented. A large set with on-chain governance replacement should not be graded as a single-party operator even if rotation is not instantaneous. A small set with informal replacement should be treated as a single-party operator.

---

### Slice: VERIFIABILITY

Evaluate whether an outsider can independently confirm what the deployed code does.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- V1. For each address you assess: is the bytecode verified on the chain's block explorer? Record the "Contract Source Code Verified" indicator. https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x... returns this as a top-level "verified" boolean plus "abiSource" ("etherscan" / "sourcify") and an inline ABI — useful when the explorer page is rate-limited. If the contract is a proxy, verify BOTH the proxy contract AND the current implementation contract. The same /api/contract/abi response auto-resolves proxies and includes a "proxy.implementation" address when present, so one call covers V1 + V6 in one shot. An explorer "Similar Match" on a well-known proxy pattern (Aragon AppProxyUpgradeable, ERC1967Proxy, OssifiableProxy, OZ TransparentUpgradeableProxy) is expected for that pattern and does NOT count as a verification gap on its own — what matters is that the implementation is independently verified.
- V2. Source-to-repo correspondence: for each verified contract, attempt to find a matching commit in the linked GitHub repos. Record evidence[].commit on a match. Independent compile/bytecode-match is NOT required for green — a recognized public repo whose structure and file contents correspond to the explorer-visible source is sufficient. If you did not pin a commit SHA or run a bytecode diff, record that plainly in unknowns[] and proceed; it is a scope limit, not a downgrade signal.
- V3. Audit coverage: for each URL in protocol.audit_links, open it and record: auditor name, audit date, the specific contracts / commit in scope. Flag audits that predate the current deployment by >6 months without a follow-up review.
- V4. Auditor recognition: the following firms are broadly recognized in Solidity: Trail of Bits, Zellic, Spearbit, OpenZeppelin, ConsenSys Diligence, Certora (formal verification), Quantstamp, Halborn, Peckshield, Sigma Prime, ChainSecurity, Ackee Blockchain, MixBytes, Statemind. Unknown firms are orange-at-best for any green-grade claim. Name the firm explicitly in evidence[].
- V5. Post-audit drift: compare the most recent in-scope audit(s) against the currently-deployed source, weighted by what each contract does and by what the changes actually contain. SCOPE — drift only downgrades the grade when ALL of the following hold: (i) the drifting contract is fund-custody / settlement / accounting-critical (NOT a peripheral router, lens, quoter, or pure-view contract that holds no balances); (ii) the changes are material — new functions, modified access control, modified accounting, modified fund flow — and not refactors / struct relocations / import reorgs / build or CI fixes / formatting; (iii) no later audit, fix-audit, or differential audit from a recognized firm covers the changed files (audits often pin a pre-fix commit while a follow-up reviews the delta — match by file scope, not by commit-hash equality). When you cite drift as a downgrade reason, name the specific behavior change (function added, role granted, accounting formula altered) — "N commits ahead" or "+X/-Y LOC" alone is not evidence of material drift. If you have not sampled the diff content (e.g. via the GitHub compare view or the top commits in the window), record drift as an unknowns[] entry rather than auto-downgrading; commit-count and LOC are starting signals, not findings.
- V6. Implementation vs proxy: a verified proxy with an unverified implementation is effectively unverified. State whether the implementation is verified separately.

EVIDENCE DISCIPLINE (read before writing findings[]):
- Do not assert a specific deploy-commit SHA, bytecode equivalence, or "identical to audited commit" unless you actually fetched the artifact that shows it (e.g., a deployed-addresses JSON you opened, an explorer page you read). Inferred or plausible matches belong in unknowns[], never in findings[] or evidence[].
- Evidence[] entries must correspond to pages/files you actually retrieved this run. A URL you did not open is not evidence.

Then write the steel-man section per Hard Rule 11.

Grade rules:
- green   = deployed bytecode verified on the explorer (proxy AND implementation if proxied; "Similar Match" on a standard proxy pattern is fine per V1), a public source repo exists whose contents correspond to the explorer-visible source, AND ≥1 audit from a recognized firm covering the currently-deployed contracts (≤6 months of drift OR drift was re-audited). A missing local compile-match is not a downgrade — record it in unknowns[] and still grade green if the other conditions hold.
- orange  = verified but with visible drift from the public repo, OR audit scope is stale relative to deployment, OR only minor / unknown-firm audits exist, OR only some of the main contracts are verified, OR proxy verified but implementation only partially verified.
- red     = unverified bytecode (or verified proxy with unverified implementation), OR no audit in protocol.audit_links, OR no public repo.
- unknown = reserved for when the protocol's verifiability posture genuinely cannot be assessed (e.g., explorer and repo both inaccessible for this protocol). Do NOT use unknown merely because you, the analyst, could not run a particular check such as a bytecode diff — that goes in unknowns[] while the grade is still assigned from the evidence you do have.

---

### JSON output contract

Return exactly one JSON array inside a single ```json fenced block. The array MUST contain exactly five objects, one per risk slice, in this exact order: "control", "ability-to-exit", "autonomy", "open-access", "verifiability". Do not include the discovery slice.

Each object has the same shape as a normal slice submission:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "<one of: control | ability-to-exit | autonomy | open-access | verifiability>",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- Produce one complete object for each of these slices only: control, ability-to-exit, autonomy, open-access, verifiability.
- Reuse the same model, chat_url, snapshot_generated_at, prompt_version, analysis_date, and slug values across all five objects.
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches that object's slice checklist prefix verbatim (C1, E2, AU3, A3b, V4a, …); unknowns[] entries are checklist-coded ("C3: …").
- Wrap the array in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Verifiability tentative 3/3 models agree AI-only 3/3 with chat share link

All inspected contracts verified on Polygonscan with public source repos and ChainSecurity / OpenZeppelin audits on V1 architecture; V2 CTFExchange + pUSD (April 2026) audits not yet in the Polymarket-published audit registry

Verdict

Choosing orange per V5: drift between the audit-registry-listed CTFExchange V1 (0x4bFb...982e) and the address_book's V2 (0xE111...996B), plus the newly-deployed UUPS-upgradeable pUSD CollateralToken on the collateral path — both are fund-custody / settlement-critical contracts whose audit reports are not present in the Polymarket-published contract-security registry as of this run — meets the rubric's orange criterion 'audit scope is stale relative to deployment' for the current production surface; the green steel-man assumes a not-yet-documented V2 audit exists, which is not affirmatively established by fetched evidence.

Steelman argument

Steelman argument The full V1 architecture (CTFExchange V1, ConditionalTokens, NegRisk modules, UmaCtfAdapter, Proxy Factory, Safe Factory) is verified on Polygonscan and audited by ChainSecurity and/or OpenZeppelin with public reports linked from the Polymarket-owned contract-security repo, but the V2 CTFExchange and pUSD deployments — both April 2026 and on the fund-custody / collateral path — are verified on Polygonscan but their audit status is not yet documented in the public registry.

Evidence (6)

V1: Verification status of inspected contracts: CTFExchange V2 (0xE111...996B) — verified on Polygonscan ('ABI source: etherscan' per defipunkd, contract name 'CTFExchange'); ConditionalTokens (0x4D97...6045) — verified ('ABI source: etherscan', name 'ConditionalTokens'); UmaCtfAdapter (0x6A9D...4F74) — verified ('Contract Source Code Verified (Exact Match)' on the Polygonscan source page, compiler 0.8.15, name 'UmaCtfAdapter'); pUSD CollateralToken proxy (0xC011...2DFB) — verified ('ABI source: etherscan', name 'CollateralToken'). The proxy/implementation pair for pUSD (proxy 0xC011...2DFB, implementation 0x6bBCef...0925f per the address_book) is identified by the ABI exposing upgradeToAndCall / proxiableUUID; the implementation itself was not directly opened in Polygonscan this run.
V2: Public source repos exist for the core stack: github.com/Polymarket/ctf-exchange (V1), github.com/Polymarket/ctf-exchange-v2 (V2, source visible), github.com/Polymarket/uma-ctf-adapter (UMA adapter source visible including the verified UmaCtfAdapter.sol with the 2-day emergencySafetyPeriod constant), github.com/Polymarket/neg-risk-ctf-adapter (Neg-Risk modules), and github.com/Polymarket/contract-security (registry of audits and deployment addresses). The Polygonscan-visible source of UmaCtfAdapter corresponds in structure (file naming, imports of Auth, BulletinBoard, libraries/TransferHelper, etc.) to the file uma-ctf-adapter/src/UmaCtfAdapter.sol in the public repo. Bytecode-equivalence diffing and explicit commit SHA pinning were not performed this run.
V3: Audit coverage per the Polymarket-published contract-security registry: ProxyFactory (0xaB45...4052) — ChainSecurity; Safe Factory (0xaacF...3541b) — ChainSecurity; ConditionalTokens (0x4D97...6045) — ChainSecurity; CTFExchange V1 (0x4bFb...982e) — ChainSecurity; NegRisk Adapter / Operator / Wrapped Collateral / CtfExchange / FeeModule / UmaCtfAdapter (the v2 multi-outcome modules) — ChainSecurity + OpenZeppelin; UmaCtfAdapter (0x6A9D...4F74) — ChainSecurity (the linked file in the registry is 'oz_uma_ctf_adapter.pdf' but the registry row labels it ChainSecurity; the UMA adapter repo separately links an OpenZeppelin audit at uma-ctf-adapter/audit/Polymarket_UMA_Optimistic_Oracle_Adapter_Audit.pdf). Audit dates are not enumerated in the registry rows; the linked audit PDFs were not opened this run.
V4: Both audit firms identified — ChainSecurity and OpenZeppelin — are on the rubric's list of recognized Solidity audit firms, so the v1 / NegRisk audit coverage meets the recognized-firm bar. No unknown audit firm needs to be considered for the V1 architecture.
V5: Post-audit drift: the V1 CTFExchange (0x4bFb...982e) is the audited deployment in the contract-security registry, but the address_book in this assessment pins the NEWER CTFExchange V2 at 0xE111...996B as the current production exchange. The ctf-exchange-v2 README (April 2026) mentions security disclosures via the 'Cantina bug bounty program' but does NOT link a published V2 audit report in the contract-security registry as of this run. pUSD CollateralToken (0xC011...2DFB) — a NEW April 2026 UUPS-upgradeable contract that holds V2 trading collateral — is likewise not in the contract-security registry. Both are fund-custody/settlement-critical surfaces by the V5 rubric. Whether a recognized-firm audit covers the deployed V2 bytecode could not be confirmed this run.
V6: Proxy/implementation: only pUSD CollateralToken (0xC011...2DFB) is a proxy among the inspected addresses. The defipunkd ABI surface for the proxy includes upgradeToAndCall and proxiableUUID (UUPS), and the pinned address_book lists 0x6bBCef...0925f as the current implementation. The implementation contract was NOT independently opened on Polygonscan this run, so 'implementation verified separately' is not affirmatively established — recorded in unknowns.

Why is this consensus tentative?

weak consensus margin

A fresh independent run can strengthen (or overturn) the verdict.

Run your own prompt Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-international
- protocol.name:              Polymarket International
- protocol.chains:            Polygon
- protocol.category:          Prediction Market
- protocol.website:           https://polymarket.com/?r=defillamareal
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               [
  {
    "chain": "Polygon",
    "address": "0xE111180000d2663C0091e4f400237545B87B996B",
    "role": "CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xe2222d279d744050d28e00520010520000310F59",
    "role": "Neg Risk CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296",
    "role": "Neg Risk Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0x4D97DCd97eC945f40cF65F87097ACe5EA0476045",
    "role": "Conditional Tokens (CTF)"
  },
  {
    "chain": "Polygon",
    "address": "0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB",
    "role": "pUSD CollateralToken (proxy)"
  },
  {
    "chain": "Polygon",
    "address": "0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f",
    "role": "pUSD CollateralToken (implementation)"
  },
  {
    "chain": "Polygon",
    "address": "0x93070a847efEf7F70739046A929D47a521F5B8ee",
    "role": "CollateralOnramp"
  },
  {
    "chain": "Polygon",
    "address": "0x2957922Eb93258b93368531d39fAcCA3B4dC5854",
    "role": "CollateralOfframp"
  },
  {
    "chain": "Polygon",
    "address": "0xebC2459Ec962869ca4c0bd1E06368272732BCb08",
    "role": "PermissionedRamp"
  },
  {
    "chain": "Polygon",
    "address": "0xAdA100Db00Ca00073811820692005400218FcE1f",
    "role": "CtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xadA2005600Dec949baf300f4C6120000bDB6eAab",
    "role": "NegRiskCtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xaacfeea03eb1561c4e67d661e40682bd20e3541b",
    "role": "Gnosis Safe Factory"
  },
  {
    "chain": "Polygon",
    "address": "0xaB45c5A4B0c941a2F231C04C3f49182e1A254052",
    "role": "Polymarket Proxy Factory"
  },
  {
    "chain": "Polygon",
    "address": "0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74",
    "role": "UMA Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0xCB1822859cEF82Cd2Eb4E6276C7916e692995130",
    "role": "UMA Optimistic Oracle"
  }
]

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
- https://defipunkd.com/address/137/0xE111180000d2663C0091e4f400237545B87B996B (CTF Exchange)
- https://defipunkd.com/address/137/0xe2222d279d744050d28e00520010520000310F59 (Neg Risk CTF Exchange)
- https://defipunkd.com/address/137/0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296 (Neg Risk Adapter)
- https://defipunkd.com/address/137/0x4D97DCd97eC945f40cF65F87097ACe5EA0476045 (Conditional Tokens (CTF))
- https://defipunkd.com/address/137/0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB (pUSD CollateralToken (proxy))
- https://defipunkd.com/address/137/0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f (pUSD CollateralToken (implementation))
- https://defipunkd.com/address/137/0x93070a847efEf7F70739046A929D47a521F5B8ee (CollateralOnramp)
- https://defipunkd.com/address/137/0x2957922Eb93258b93368531d39fAcCA3B4dC5854 (CollateralOfframp)
- https://defipunkd.com/address/137/0xebC2459Ec962869ca4c0bd1E06368272732BCb08 (PermissionedRamp)
- https://defipunkd.com/address/137/0xAdA100Db00Ca00073811820692005400218FcE1f (CtfCollateralAdapter)
- https://defipunkd.com/address/137/0xadA2005600Dec949baf300f4C6120000bDB6eAab (NegRiskCtfCollateralAdapter)
- https://defipunkd.com/address/137/0xaacfeea03eb1561c4e67d661e40682bd20e3541b (Gnosis Safe Factory)
- https://defipunkd.com/address/137/0xaB45c5A4B0c941a2F231C04C3f49182e1A254052 (Polymarket Proxy Factory)
- https://defipunkd.com/address/137/0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74 (UMA Adapter)
- https://defipunkd.com/address/137/0xCB1822859cEF82Cd2Eb4E6276C7916e692995130 (UMA Optimistic Oracle)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: VERIFIABILITY

Evaluate whether an outsider can independently confirm what the deployed code does.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- V1. For each address you assess: is the bytecode verified on the chain's block explorer? Record the "Contract Source Code Verified" indicator. https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x... returns this as a top-level "verified" boolean plus "abiSource" ("etherscan" / "sourcify") and an inline ABI — useful when the explorer page is rate-limited. If the contract is a proxy, verify BOTH the proxy contract AND the current implementation contract. The same /api/contract/abi response auto-resolves proxies and includes a "proxy.implementation" address when present, so one call covers V1 + V6 in one shot. An explorer "Similar Match" on a well-known proxy pattern (Aragon AppProxyUpgradeable, ERC1967Proxy, OssifiableProxy, OZ TransparentUpgradeableProxy) is expected for that pattern and does NOT count as a verification gap on its own — what matters is that the implementation is independently verified.
- V2. Source-to-repo correspondence: for each verified contract, attempt to find a matching commit in the linked GitHub repos. Record evidence[].commit on a match. Independent compile/bytecode-match is NOT required for green — a recognized public repo whose structure and file contents correspond to the explorer-visible source is sufficient. If you did not pin a commit SHA or run a bytecode diff, record that plainly in unknowns[] and proceed; it is a scope limit, not a downgrade signal.
- V3. Audit coverage: for each URL in protocol.audit_links, open it and record: auditor name, audit date, the specific contracts / commit in scope. Flag audits that predate the current deployment by >6 months without a follow-up review.
- V4. Auditor recognition: the following firms are broadly recognized in Solidity: Trail of Bits, Zellic, Spearbit, OpenZeppelin, ConsenSys Diligence, Certora (formal verification), Quantstamp, Halborn, Peckshield, Sigma Prime, ChainSecurity, Ackee Blockchain, MixBytes, Statemind. Unknown firms are orange-at-best for any green-grade claim. Name the firm explicitly in evidence[].
- V5. Post-audit drift: compare the most recent in-scope audit(s) against the currently-deployed source, weighted by what each contract does and by what the changes actually contain. SCOPE — drift only downgrades the grade when ALL of the following hold: (i) the drifting contract is fund-custody / settlement / accounting-critical (NOT a peripheral router, lens, quoter, or pure-view contract that holds no balances); (ii) the changes are material — new functions, modified access control, modified accounting, modified fund flow — and not refactors / struct relocations / import reorgs / build or CI fixes / formatting; (iii) no later audit, fix-audit, or differential audit from a recognized firm covers the changed files (audits often pin a pre-fix commit while a follow-up reviews the delta — match by file scope, not by commit-hash equality). When you cite drift as a downgrade reason, name the specific behavior change (function added, role granted, accounting formula altered) — "N commits ahead" or "+X/-Y LOC" alone is not evidence of material drift. If you have not sampled the diff content (e.g. via the GitHub compare view or the top commits in the window), record drift as an unknowns[] entry rather than auto-downgrading; commit-count and LOC are starting signals, not findings.
- V6. Implementation vs proxy: a verified proxy with an unverified implementation is effectively unverified. State whether the implementation is verified separately.

EVIDENCE DISCIPLINE (read before writing findings[]):
- Do not assert a specific deploy-commit SHA, bytecode equivalence, or "identical to audited commit" unless you actually fetched the artifact that shows it (e.g., a deployed-addresses JSON you opened, an explorer page you read). Inferred or plausible matches belong in unknowns[], never in findings[] or evidence[].
- Evidence[] entries must correspond to pages/files you actually retrieved this run. A URL you did not open is not evidence.

Then write the steel-man section per Hard Rule 11.

Grade rules:
- green   = deployed bytecode verified on the explorer (proxy AND implementation if proxied; "Similar Match" on a standard proxy pattern is fine per V1), a public source repo exists whose contents correspond to the explorer-visible source, AND ≥1 audit from a recognized firm covering the currently-deployed contracts (≤6 months of drift OR drift was re-audited). A missing local compile-match is not a downgrade — record it in unknowns[] and still grade green if the other conditions hold.
- orange  = verified but with visible drift from the public repo, OR audit scope is stale relative to deployment, OR only minor / unknown-firm audits exist, OR only some of the main contracts are verified, OR proxy verified but implementation only partially verified.
- red     = unverified bytecode (or verified proxy with unverified implementation), OR no audit in protocol.audit_links, OR no public repo.
- unknown = reserved for when the protocol's verifiability posture genuinely cannot be assessed (e.g., explorer and repo both inaccessible for this protocol). Do NOT use unknown merely because you, the analyst, could not run a particular check such as a bytecode diff — that goes in unknowns[] while the grade is still assigned from the evidence you do have.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "verifiability",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Sources claude-opus-4-7 url ↗ gpt-5.5-thinking url ↗ grok-3 url ↗ View raw submissions ↗

Control tentative 3/3 models agree AI-only 3/3 with chat share link

Multiple T1 admin powers reachable with short or zero delay: UMA Adapter emergency-resolve (2-day), pUSD V2 UUPS upgrade (no timelock); admin holders unidentified

Verdict

Choosing orange because the T1 paths are real and on the uncontested fast path with delays well under 7 days (0d for pUSD upgrade, 2d for emergencyResolve), but the admin/owner identities were not re-verified on-chain this run, so the rubric's 'EOA or 2-of-3 with no timelock' red trigger is not affirmatively shown — orange (failing-Security-Council multisig on a T1 path with <7d effective delay) is the steel-man best supported by the inspected ABIs.

Steelman argument

Steelman argument T1 is reachable on the uncontested fast path with delays of 0 days (pUSD upgrade) and 2 days (UMA emergency resolve), both under the 7-day bar required for green, while the most likely admin class — an internal Polymarket operations multisig — fails Security Council criteria but is not affirmatively a 2-of-3 or EOA.

Evidence (7)

C1: UmaCtfAdapter (0x6A9D...4F74) exposes onlyAdmin functions flag, pause, unpause, emergencyResolve, reset, addAdmin, removeAdmin, renounceAdmin. ConditionalTokens (0x4D97...6045) has no admin/owner functions visible on its ABI — fully immutable. CTFExchange V2 (0xE111...996B) exposes isAdmin/addAdmin/removeAdmin and admin-gated pauseTrading/unpauseTrading/setFeeReceiver/setMaxFeeRate/setUserPauseBlockInterval. pUSD CollateralToken proxy (0xC011...2DFB) is Solady Ownable + UUPS and exposes owner(), transferOwnership, grantRoles/revokeRoles, addMinter/addWrapper, mint/burn, and upgradeToAndCall. Specific admin holder addresses were not read on-chain this run (RPC tenant disabled on defipunkd surfacer; see unknowns).
C2: Upgradeability is MIXED across the system. ConditionalTokens, CTFExchange V1 (0x4bFb...982e) and V2, UmaCtfAdapter are constructor-only implementations with no upgrade entry point visible on their ABIs (immutable). pUSD CollateralToken proxy at 0xC011...2DFB is UUPS-upgradeable: ABI exposes upgradeToAndCall(address newImplementation,bytes data) and proxiableUUID(); current implementation pointer is 0x6bBCef...0925f per pinned address_book. A4 Polymarket Proxy Factory (0xaB45...4052) deploys per-user proxy wallets — those are 1-of-1 user-owned multisigs, NOT a protocol-admin upgrade surface, and are documented as such in the Polymarket proxy-wallet docs.
C3: EXECUTION PATH for the highest-tier admin actions has effectively NO multi-stage timelock. (a) pUSD V2 upgrade: owner() → upgradeToAndCall(impl, data) in a single transaction, delay 0 seconds. No scheduler / timelock contract is referenced in the proxy ABI. (b) UMA Adapter emergency override: admin → flag(questionID) sets emergencyResolutionTimestamp = block.timestamp + emergencySafetyPeriod, where emergencySafetyPeriod is a public constant = 2 days (172800 s) per the verified Polygonscan source; admin then waits ≥2 days and calls emergencyResolve(questionID, payouts) which writes arbitrary [YES,NO] payouts directly to ctf.reportPayouts. (c) UMA Adapter pause(questionID): admin → pause(questionID) sets paused=true with NO time cap on individual questions. (d) CTFExchange V2 admin: admin → pauseTrading()/setMaxFeeRate(rate)/setFeeReceiver(addr) in a single transaction, delay 0 seconds.
C4: Privileged actors and their scope: (i) pUSD owner — single owner() role on a UUPS proxy, holds T1 power to replace implementation bytecode (entire token + minter logic). Identity not re-verified on-chain this run. (ii) UmaCtfAdapter admins() — uint256-mapped role set (count unknown), each can flag/pause/emergencyResolve any market; T1 per market. (iii) CTFExchange V1 and V2 admin set — each admin can pauseTrading globally and tune fees up to a max cap; T1 for trading-availability and T2 for fee economics. None of these are identified as Gnosis Safes by ABI inspection alone, and a 'Security Council' (≥7 signers, ≥51% threshold, ≥50% non-insider, publicly announced) is not documented for Polymarket; the protocol's published proxy-wallet system is for end-users, not for protocol governance.
C5: No on-chain Governor / GovernorBravo / Aragon Voting / OZ Governor contract is present in the address_book or surfaced from the inspected contracts. Polymarket's POLY governance token has been publicly announced but is unlaunched as of 2026-05-18, so no token-weighted on-chain governance currently exists. Governance is therefore admin-key based, not vote-based.
C6: UmaCtfAdapter has a dedicated emergency-pause path (flag → 2-day safety period → emergencyResolve) separate from the standard pause()/unpause(). Both routes are held by the same onlyAdmin role — there is no separate guardian role with shorter time bound or different actor; the only time-bound is the 2-day emergencySafetyPeriod for arbitrary-payout resolution, while regular pause(questionID) is uncapped.
C7: HIGHEST tier reachable on the uncontested fast path is T1 (FUND-CRITICAL): (a) pUSD owner can upgrade implementation to bytecode that mints unlimited pUSD or transfers the underlying USDC/USDCe vault out — directly impairs collateral backing of every V2 market, with zero on-chain delay; (b) UmaCtfAdapter admin can emergencyResolve any flagged market with arbitrary [YES,NO] payouts after the 2-day safety period, redirecting that market's locked collateral to the chosen side. Lower-tier T2 surfaces also exist (setMaxFeeRate within bounds, fee receiver change). Per rubric, T1 reachable with no timelock OR <7-day delay = orange or red; red requires positive evidence of EOA / 2-of-3 admin holder, which was not established this run.

Why is this consensus tentative?

weak consensus margin

A fresh independent run can strengthen (or overturn) the verdict.

Run your own prompt Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-international
- protocol.name:              Polymarket International
- protocol.chains:            Polygon
- protocol.category:          Prediction Market
- protocol.website:           https://polymarket.com/?r=defillamareal
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               [
  {
    "chain": "Polygon",
    "address": "0xE111180000d2663C0091e4f400237545B87B996B",
    "role": "CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xe2222d279d744050d28e00520010520000310F59",
    "role": "Neg Risk CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296",
    "role": "Neg Risk Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0x4D97DCd97eC945f40cF65F87097ACe5EA0476045",
    "role": "Conditional Tokens (CTF)"
  },
  {
    "chain": "Polygon",
    "address": "0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB",
    "role": "pUSD CollateralToken (proxy)"
  },
  {
    "chain": "Polygon",
    "address": "0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f",
    "role": "pUSD CollateralToken (implementation)"
  },
  {
    "chain": "Polygon",
    "address": "0x93070a847efEf7F70739046A929D47a521F5B8ee",
    "role": "CollateralOnramp"
  },
  {
    "chain": "Polygon",
    "address": "0x2957922Eb93258b93368531d39fAcCA3B4dC5854",
    "role": "CollateralOfframp"
  },
  {
    "chain": "Polygon",
    "address": "0xebC2459Ec962869ca4c0bd1E06368272732BCb08",
    "role": "PermissionedRamp"
  },
  {
    "chain": "Polygon",
    "address": "0xAdA100Db00Ca00073811820692005400218FcE1f",
    "role": "CtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xadA2005600Dec949baf300f4C6120000bDB6eAab",
    "role": "NegRiskCtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xaacfeea03eb1561c4e67d661e40682bd20e3541b",
    "role": "Gnosis Safe Factory"
  },
  {
    "chain": "Polygon",
    "address": "0xaB45c5A4B0c941a2F231C04C3f49182e1A254052",
    "role": "Polymarket Proxy Factory"
  },
  {
    "chain": "Polygon",
    "address": "0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74",
    "role": "UMA Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0xCB1822859cEF82Cd2Eb4E6276C7916e692995130",
    "role": "UMA Optimistic Oracle"
  }
]

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
- https://defipunkd.com/address/137/0xE111180000d2663C0091e4f400237545B87B996B (CTF Exchange)
- https://defipunkd.com/address/137/0xe2222d279d744050d28e00520010520000310F59 (Neg Risk CTF Exchange)
- https://defipunkd.com/address/137/0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296 (Neg Risk Adapter)
- https://defipunkd.com/address/137/0x4D97DCd97eC945f40cF65F87097ACe5EA0476045 (Conditional Tokens (CTF))
- https://defipunkd.com/address/137/0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB (pUSD CollateralToken (proxy))
- https://defipunkd.com/address/137/0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f (pUSD CollateralToken (implementation))
- https://defipunkd.com/address/137/0x93070a847efEf7F70739046A929D47a521F5B8ee (CollateralOnramp)
- https://defipunkd.com/address/137/0x2957922Eb93258b93368531d39fAcCA3B4dC5854 (CollateralOfframp)
- https://defipunkd.com/address/137/0xebC2459Ec962869ca4c0bd1E06368272732BCb08 (PermissionedRamp)
- https://defipunkd.com/address/137/0xAdA100Db00Ca00073811820692005400218FcE1f (CtfCollateralAdapter)
- https://defipunkd.com/address/137/0xadA2005600Dec949baf300f4C6120000bDB6eAab (NegRiskCtfCollateralAdapter)
- https://defipunkd.com/address/137/0xaacfeea03eb1561c4e67d661e40682bd20e3541b (Gnosis Safe Factory)
- https://defipunkd.com/address/137/0xaB45c5A4B0c941a2F231C04C3f49182e1A254052 (Polymarket Proxy Factory)
- https://defipunkd.com/address/137/0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74 (UMA Adapter)
- https://defipunkd.com/address/137/0xCB1822859cEF82Cd2Eb4E6276C7916e692995130 (UMA Optimistic Oracle)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: CONTROL

Evaluate who can change the protocol's rules, how fast, and how broadly.

(Step 0 capability probe and the off-chain-only fallback live in the preamble — those rules apply here.)

### MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[])

- **C1.** For each address you assess: who is the contract owner / admin / pendingAdmin / governor — read these via the block explorer's "Read Contract" tab OR `https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=owner` (BARE method names: `&method=owner`, `&method=admin`, `&method=pendingOwner`, `&method=governor`). For Safes use `/api/safe/owners?chainId=<id>&address=0x...`. When a protocol has multiple major versions deployed (v2/v3/v4), perform C1 reads on the NEWEST deployment separately — newer deployments often have weaker control surfaces than the legacy core.
- **C2.** Upgrade mechanism: transparent proxy / UUPS / Beacon / Diamond / immutable. Identify the proxy admin address. Check upgradeability of GOVERNANCE contracts too — a Governor / Aragon Voting / OZ Governor is often itself a proxy whose admin is the Timelock. Asymmetry: when fund-holding cores are immutable AND governance has no admin path that reaches them, an upgradable Governor/Timelock is T3-only and must NOT drag the verdict below green on that basis alone (see grade rules and the "immutable cores" caveat). Only call upgradability "mixed" if you can name a concrete function on the upgradable surface that reaches T1 or T2 on user funds.
- **C3.** EXECUTION PATH (enumerate every stage, in order, with delays in seconds). The operative path is usually a chain (voting → scheduler → timelock → executor; or governor → queue → execute; or Aragon Voting → DualGovernance → EmergencyProtectedTimelock → AdminExecutor). For each stage, record (a) the contract address, (b) the delay constant name + value in seconds, (c) the URL you read it from (block-explorer Read Contract OR `/api/contract/read?...&method=MIN_DELAY&block=<n>`). Do NOT stop at the first timelock-shaped contract — if its admin is itself called by another contract, keep walking. The grading delay is the SUM OF DELAYS ON THE UNCONTESTED FAST PATH (shortest time a proposal with no opposition can go from submission to executable). Dynamic / contested extensions (veto signaling, rage quit, escrow delay) are modifiers, not the basis — note them separately.
- **C4.** Enumerate EVERY multisig with reachable control — main proxy admin, emergency activation, emergency execution, reseal / pause, gate-seal committees, tiebreaker, per-module admins. For each Safe, fetch threshold + owners + version via `/api/safe/owners?chainId=<id>&address=0x...` (response includes raw eth_call data, so the URL is citable evidence). Enumerate ops/council/incentives multisigs even when off the upgrade path — record their scope so a reader can see they are NOT on the upgrade path. For each: (a) address, (b) threshold / total signers, (c) signer identities classified as insider (team, paid auditors under ongoing engagement, mandated service providers) vs non-insider (independent community members, unaffiliated researchers), (d) the specific power held (upgrade, pause, parameter, etc.).
- **C5.** On-chain governance: Governor / GovernorBravo / OZ Governor / Aragon Voting with token-weighted voting? Record proposal threshold, voting period, quorum, and the timelock delay between queue and execute. Every numeric constant must come from a Read Contract call you can link to, or be in unknowns[] with the C-code. If votingDelay / votingPeriod are denominated in BLOCKS, convert to seconds at the chain's CURRENT block time (Ethereum mainnet ≈ 12s post-Merge, not the 15s in older Compound/Bravo deployments) — cite both block count and converted seconds.
- **C6.** EMERGENCY POWERS: separate emergency-pause / guardian role with a different time cap or different actor than the main upgrade authority? Record it explicitly.
- **C7.** POWER TIER (blast radius). For each privileged path in C3–C6, classify the WORST thing that path can do, choosing the highest applicable tier. Cite the specific function name and any on-chain bound — tier claims without a named function are unsupported.
    - **T1 — FUND-CRITICAL**: replace implementation of contracts holding user funds; change AMM math / accounting / collateral logic; mint unbacked debt or shares; pause withdrawals; drain user-fund treasury; change oracle to attacker-controlled source; replace upgrade admin with EOA.
    - **T2 — ECONOMICALLY MATERIAL**: change fee parameters within bounded ranges; redirect protocol fees; add/remove markets / collateral types; bounded inflation or token mint within hard-capped schedule; spend protocol-owned (non-user) treasury.
    - **T3 — GOVERNANCE-INTERNAL**: change voting rules, quorum, voting period, proposal threshold; upgrade the Governor itself; rotate Timelock admin; mint governance tokens within a capped annual schedule.
    - **T4 — OPERATIONAL**: incentives distribution, grants, ENS / frontend canonicalization, deployment coordination, periphery router deprecation.
  The grade is set by the HIGHEST tier reachable on the uncontested fast path, not the median. State the tier and the binding function in the verdict.

### Read Contract discipline (applies to C3, C4, C5)

Every numeric constant cited (timelock delays, voting periods, multisig thresholds, quorum percentages) must come from EITHER (a) a block-explorer Read Contract URL, OR (b) a DeFiPunkd `/api/contract/read` or `/api/safe/owners` URL (preferred with `&block=<n>` for content-addressed evidence), OR (c) an unknowns[] entry with the C-code. Docs / blog posts are corroboration only — they cannot be the sole citation for a value that is also readable on-chain.

### Off-chain-only substitute hierarchy (when grading_basis="off-chain-only" — see preamble Rule 16)

When on-chain reads were genuinely unreachable this run, eligible off-chain substitutes in priority order:
1. Linked audit PDFs (admin roles, multisig members, timelock delays usually enumerated).
2. Governance forum posts that quote constants from a successful on-chain proposal (cite post URL + linked execution-tx URL).
3. Official protocol docs pages with named addresses and roles (must be on a domain owned by the protocol).
4. GitHub README / SECURITY.md / governance/*.md at a pinned commit SHA.

Forbidden substitutes: third-party blog posts, X / Twitter threads, search-result snippets, model memory. Required degradation: any C-code citing a numeric constant from docs/forum/audit prose ONLY must also carry an `unknowns[]` entry with `-offchain` suffix noting "value not re-read on-chain in this run; corroboration only".

### Grade rules (apply the timelock bar conditional on the highest C7 tier reachable on the fast path)

Security Council standard (used below): a multisig qualifies as "Security Council" only if ALL of: ≥7 signers, ≥51% threshold, ≥50% non-insider signers, every signer publicly announced. Failing any criterion = NOT a Security Council, regardless of signer reputation.

- **green**: highest reachable tier is T3 or T4 regardless of timelock; OR T2 reachable with uncontested-fast-path delay ≥7 days; OR T1 reachable only via immutable contracts (T1 is unreachable); OR T1 reachable with uncontested-fast-path delay ≥7 days combined with a Security Council multisig; OR T1 reachable with uncontested-fast-path delay ≥7 days through active on-chain governance with broad token distribution.
- **orange**: T2 reachable with uncontested-fast-path delay >0 but <7 days; OR T1 reachable with uncontested-fast-path delay >0 but <7 days; OR a multisig failing one or more Security Council criteria sits on a T1/T2 path; OR unclear upgrade authority on a T1/T2 path; OR governance with very short timelock or low quorum on a T1/T2 path.
- **red**: T1 reachable with no timelock by a single EOA or 2-of-3 multisig; OR a T1 upgrade admin that is not a smart contract you can audit.
- **unknown**: completed the checklist but still cannot determine the upgrade authority OR cannot classify the highest tier reachable on the main contracts.

Tiering caveats:
- "Bounded" must be enforced ON-CHAIN to count as T2. A function that sets fees with no upper-bound check is T1 — cite the bound check.
- Recurring T2 economic extraction (e.g. fee redirect with no rate limit) approaches T1 over time. A single proposal that can permanently redirect all future revenue is T1.
- T3 assumes the governance contract cannot itself authorize a T1/T2 action without going through the same timelock. If governance can self-upgrade to bypass the timelock, T3 collapses into T1.
- Do not downgrade tier by hand-waving ("realistically governance would never…"). Tier on what the contract permits, not what feels likely.

Notes:
- **Dynamic / dual-governance timelocks** (Lido, Compound escrow veto): the rubric grades on the uncontested path because that is the path most upgrades take. A dynamic extension that fires only under stake-weighted opposition is a real protection — name it in the green steel-man, but it does not lift an orange fast path into green; state the tension in the verdict.
- **Immutable cores with upgradable governance** (Uniswap-style): if fund-holding contracts are immutable and have no admin-reachable function moving / freezing / re-routing user funds, the highest reachable tier on the upgrade path is T3 — green regardless of timelock. Don't grade this orange just because the Governor is a proxy — that's a C2 fact, not a downgrade. Downgrade only applies if you can cite a concrete function on the upgradable surface that reaches T1 or T2 (privileged hook, upgradable factory controlling fund-routing, fee-switch redirecting protocol revenue without bound).
- **The 7-day bar** reflects the exit-window standard — users need notice after a queued upgrade to withdraw if they disagree. The ability-to-exit slice grades the exit side; this slice grades the delay side; both must hold for users to actually benefit from the delay.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "control",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Sources claude-opus-4-7 url ↗ gpt-5.5-thinking url ↗ grok-3 url ↗ View raw submissions ↗

Ability to exit tentative 3/3 models agree AI-only 3/3 with chat share link

Claims on already-resolved markets are permissionless on the immutable CTF, but resolution of pending markets can be paused indefinitely by the UMA Adapter admin

Verdict

Choosing orange because the rubric's orange definition fits exactly: 'claims-of-finalized are exempt but new-request placement can be paused indefinitely by governance' — already-resolved redeemPositions on the immutable CTF is unstoppable, but UmaCtfAdapter.pause(questionID) is uncapped and held by a single onlyAdmin role, so users with one-sided positions in a pending market depend on the admin to allow resolution; the green steel-man understates this lock-in for unbalanced holders in paused markets.

Steelman argument

Steelman argument Claims on already-resolved markets are unconditional and immutable on the CTF, but new-resolution placement for a pending market can be paused indefinitely by a single admin role without any time cap, so the pending-market exit story has a real centralized lever even though it is bounded to specific paused questions.

Evidence (7)

E1: User-facing exit functions live on the ConditionalTokens contract (0x4D97...6045), not on the CTFExchange. Inspected ABI exposes: redeemPositions(address,bytes32,bytes32,uint256[]) — claim winnings after resolution; mergePositions(address,bytes32,bytes32,uint256[],uint256) — burn balanced YES+NO shares back to collateral; splitPosition(address,bytes32,bytes32,uint256[],uint256) — deposit collateral and mint YES+NO; safeTransferFrom / safeBatchTransferFrom — transfer position shares away. No 'withdraw' or 'requestWithdrawal' function; positions are ERC-1155, so 'exit' = redeemPositions for resolved markets, mergePositions for unresolved balanced positions, or transfer to a peer.
E2: Access modifiers on the CTF exit functions: redeemPositions, mergePositions, splitPosition, safeTransferFrom, safeBatchTransferFrom are all public/external with no onlyOwner / onlyRole / whenNotPaused guard — the ABI does not include any pause(), paused(), or hasRole() functions on ConditionalTokens, and the contract has no admin (see CONTROL slice C1). REQUEST placement on a market (splitPosition) and CLAIM of a resolved market (redeemPositions) are both unconditional once the relevant condition state is met (resolved or not).
E3: No PAUSE_ROLE / GUARDIAN role exists on ConditionalTokens. The role-holder reads requested by the checklist (hasRole, getRoleAdmin, paused/isPaused) are not in the contract's ABI at all because the contract is built on the OpenZeppelin v0.7-era pattern without AccessControl. The only path that can block a user from reaching the redeemable state is upstream: the UmaCtfAdapter (0x6A9D...4F74) admin can call pause(bytes32 questionID) with no time cap on individual questions, preventing ctf.reportPayouts from being written for that question. This does NOT pause the redemption itself — it pauses RESOLUTION (the upstream input to the CTF).
E4: Distinct EMERGENCY vs GOVERNANCE pause paths on UmaCtfAdapter: (a) pause(questionID) onlyAdmin — no time cap, can be left set indefinitely; (b) flag(questionID) + emergencyResolve(questionID, payouts) onlyAdmin — flag sets a 2-day safety timer, after which arbitrary payouts can be written. There is no on-chain governance-vote layer above these — both are held by the same admin role. No actor exists that is time-capped at a shorter horizon than the admin.
E5: There is no queued-redemption mechanism with a daily cap or queue duration: redeemPositions on the CTF is one-shot and immediate once payouts are reported. There is also no protocol-level cap on the amount that can be redeemed per block.
E6: There is NO permissionless emergency-exit / escape-hatch that lets a user redeem an UNRESOLVED market without oracle resolution. Users holding one-sided positions in a market the admin has paused indefinitely have to either wait for unpause, hold the ERC-1155 tokens forever, sell them on the secondary market, or — if they can acquire the opposite-side tokens to make a balanced YES+NO pair — call mergePositions to recover the underlying collateral. mergePositions is permissionless and is the only adversarial-admin exit path for pending markets.
E7: Exit functions are directly callable on-chain without Polymarket's frontend: the Polymarket-published polymarket-cli (github.com/Polymarket/polymarket-cli) documents 'polymarket ctf redeem --condition 0xCONDITION...' and 'polymarket ctf merge --condition 0xCONDITION... --amount 10' as direct CTF calls; users can equivalently invoke redeemPositions / mergePositions from Etherscan-Write, a generic wallet, or any custom tooling. No frontend dependency for exit.

Why is this consensus tentative?

weak consensus margin

A fresh independent run can strengthen (or overturn) the verdict.

Run your own prompt Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-international
- protocol.name:              Polymarket International
- protocol.chains:            Polygon
- protocol.category:          Prediction Market
- protocol.website:           https://polymarket.com/?r=defillamareal
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               [
  {
    "chain": "Polygon",
    "address": "0xE111180000d2663C0091e4f400237545B87B996B",
    "role": "CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xe2222d279d744050d28e00520010520000310F59",
    "role": "Neg Risk CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296",
    "role": "Neg Risk Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0x4D97DCd97eC945f40cF65F87097ACe5EA0476045",
    "role": "Conditional Tokens (CTF)"
  },
  {
    "chain": "Polygon",
    "address": "0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB",
    "role": "pUSD CollateralToken (proxy)"
  },
  {
    "chain": "Polygon",
    "address": "0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f",
    "role": "pUSD CollateralToken (implementation)"
  },
  {
    "chain": "Polygon",
    "address": "0x93070a847efEf7F70739046A929D47a521F5B8ee",
    "role": "CollateralOnramp"
  },
  {
    "chain": "Polygon",
    "address": "0x2957922Eb93258b93368531d39fAcCA3B4dC5854",
    "role": "CollateralOfframp"
  },
  {
    "chain": "Polygon",
    "address": "0xebC2459Ec962869ca4c0bd1E06368272732BCb08",
    "role": "PermissionedRamp"
  },
  {
    "chain": "Polygon",
    "address": "0xAdA100Db00Ca00073811820692005400218FcE1f",
    "role": "CtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xadA2005600Dec949baf300f4C6120000bDB6eAab",
    "role": "NegRiskCtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xaacfeea03eb1561c4e67d661e40682bd20e3541b",
    "role": "Gnosis Safe Factory"
  },
  {
    "chain": "Polygon",
    "address": "0xaB45c5A4B0c941a2F231C04C3f49182e1A254052",
    "role": "Polymarket Proxy Factory"
  },
  {
    "chain": "Polygon",
    "address": "0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74",
    "role": "UMA Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0xCB1822859cEF82Cd2Eb4E6276C7916e692995130",
    "role": "UMA Optimistic Oracle"
  }
]

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
- https://defipunkd.com/address/137/0xE111180000d2663C0091e4f400237545B87B996B (CTF Exchange)
- https://defipunkd.com/address/137/0xe2222d279d744050d28e00520010520000310F59 (Neg Risk CTF Exchange)
- https://defipunkd.com/address/137/0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296 (Neg Risk Adapter)
- https://defipunkd.com/address/137/0x4D97DCd97eC945f40cF65F87097ACe5EA0476045 (Conditional Tokens (CTF))
- https://defipunkd.com/address/137/0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB (pUSD CollateralToken (proxy))
- https://defipunkd.com/address/137/0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f (pUSD CollateralToken (implementation))
- https://defipunkd.com/address/137/0x93070a847efEf7F70739046A929D47a521F5B8ee (CollateralOnramp)
- https://defipunkd.com/address/137/0x2957922Eb93258b93368531d39fAcCA3B4dC5854 (CollateralOfframp)
- https://defipunkd.com/address/137/0xebC2459Ec962869ca4c0bd1E06368272732BCb08 (PermissionedRamp)
- https://defipunkd.com/address/137/0xAdA100Db00Ca00073811820692005400218FcE1f (CtfCollateralAdapter)
- https://defipunkd.com/address/137/0xadA2005600Dec949baf300f4C6120000bDB6eAab (NegRiskCtfCollateralAdapter)
- https://defipunkd.com/address/137/0xaacfeea03eb1561c4e67d661e40682bd20e3541b (Gnosis Safe Factory)
- https://defipunkd.com/address/137/0xaB45c5A4B0c941a2F231C04C3f49182e1A254052 (Polymarket Proxy Factory)
- https://defipunkd.com/address/137/0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74 (UMA Adapter)
- https://defipunkd.com/address/137/0xCB1822859cEF82Cd2Eb4E6276C7916e692995130 (UMA Optimistic Oracle)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: ABILITY-TO-EXIT

Evaluate whether users can withdraw their funds on their own terms, even under adversarial admin conditions.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- E1. Enumerate every user-facing exit function in the main contracts: withdraw, redeem, burn, requestWithdrawal, claim, exit, etc. List them by name. Do NOT treat the contract as a monolith.
- E2. For EACH exit function in E1: identify its access modifiers and any pause guards (e.g. _checkResumed, whenNotPaused, onlyRole). Functions that gate REQUEST PLACEMENT often differ from functions that CLAIM FINALIZED FUNDS — check both separately.
- E3. For each pause guard: identify the role holder (which address holds PAUSE_ROLE / GUARDIAN / etc.) and the maximum pause duration. Specifically check whether PAUSE_INFINITELY (or equivalent uncapped pause) is callable, and which actor can call it (single multisig vs governance vote). For role-holder reads use https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=hasRole&args=0x...,0x... or &method=getRoleAdmin&args=0x.... For "is currently paused" checks use &method=paused or &method=isPaused&args=<resume-code>. Use the BARE method name (no parens). Cite the URL with &block=<n> in evidence[].
- E4. EMERGENCY vs GOVERNANCE pause distinction: many protocols have a fast-acting emergency pause capped at N days and a slow governance pause that can be indefinite. Record both paths separately if present, with their time caps and actor classes.
- E5. Queued redemption: documented maximum queue duration, daily withdrawal caps, whether the queue itself is pausable.
- E6. Forced-exit / escape-hatch / permissionless emergency-exit mechanism for adversarial-admin scenarios.
- E7. Frontend dependency: confirm exit functions are directly callable on-chain (e.g. via Etherscan write tab or a generic wallet) without the project's frontend.

Then write the steel-man section per Hard Rule 11. Common red-vs-orange tension on this slice: indefinite pause exists (suggests red) BUT the realistic emergency path is time-capped AND claims of already-finalized exits are not pause-gated (suggests orange). Resolve this by stating who can do what for how long, not by stopping at the worst-case sentence.

Grade rules:
- green   = permissionless exit; pause is either absent, narrowly scoped to clearly-described emergencies with auto-expiry, or capped at ≤7 days; no frontend dependency for exit; claims of already-finalized exits are not pause-gated under any path.
- orange  = pausable with broad scope OR indefinite pause is reachable only through governance vote (not unilateral admin action), OR queued redemption with documented max > 7 days, OR claims-of-finalized are exempt but new-request placement can be paused indefinitely by governance.
- red     = exit requires admin signature, OR ANY actor (including governance) can pause CLAIMS of finalized exits indefinitely, OR there is no on-chain exit function at all (purely custodial), OR pause is held by a single EOA / 2-of-3 multisig with no time cap.
- unknown = checklist incomplete after checking the sources above.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "ability-to-exit",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Sources claude-opus-4-7 url ↗ gpt-5.5-thinking url ↗ grok-3 url ↗ View raw submissions ↗

Autonomy tentative 3/3 models agree AI-only 3/3 with chat share link

Resolution hinges on UMA Optimistic Oracle (with 2hr-liveness dispute + admin emergencyResolve fallback); V2 collateral depends on Polygon PoS bridge (USDC.e) — single-dependency failure bounded to specific markets

Verdict

Choosing orange because A1 + A2 + A3 establish that UMA misbehavior or a Polygon PoS bridge failure on USDC.e CAN cause loss of user principal in affected markets — the autonomy-red criterion — but the live A6 fallbacks (permissionless dispute, ignorePrice reset, on-chain {0,0.5,1} sanity check, 2-day emergencyResolve) keep the impacted TVS bounded to specific markets rather than the entire protocol, which is the orange/Stage-1 definition; impacted TVS for a single bad UMA resolution is on the order of the affected market's collateral (typically <1% of total protocol TVS for a single market, ~unclear for the whole V1→V2 USDC.e exposure).

Steelman argument

Steelman argument Failures of the UMA oracle or the USDC.e PoS bridge can cause material principal loss in affected markets, but multiple live fallbacks (dispute mechanism, ignorePrice reset, on-chain payout sanity check forcing price ∈ {0, 0.5, 1}, 2-day admin emergencyResolve) bound the per-failure impact to specific markets rather than the whole protocol.

Evidence (9)

A1: External contracts the core stack calls or reads: (i) UMA Optimistic Oracle V2 — resolved at construction via finder.getImplementationAddress('OptimisticOracleV2') and stored as immutable on the UmaCtfAdapter; (ii) UMA Address Whitelist — read via the same finder for collateral validation; (iii) ConditionalTokens — the immutable settlement layer the adapter reports payouts to. CTFExchange V2 calls the pUSD CollateralToken (0xC011...2DFB) and the CtfCollateralAdapter (0xAdA1...Ce1f). pUSD itself wraps the real underlying collateral tokens (USDC and USDC.e per its constructor signature usdc / usdce / vault). No Chainlink, Pyth, or RedStone price feeds are referenced in any of the inspected ABIs — pricing is order-book driven, not oracle-priced.
A2: Off-chain actors that report into the protocol: the UMA Optimistic Oracle proposer/disputer set (permissionless — anyone can propose or dispute by posting the proposalBond) and the UMA DVM token-holder dispute resolution committee (escalated to on dispute). Mis-reporting by UMA can write incorrect payouts to the CTF, directly redirecting user principal in affected markets. Polymarket's own operator (matching engine) is NOT in this category — it cannot mint or redeem on its own; it can only settle matched orders. Validators / node-operators are not in scope (Polygon PoS substrate, not a Polymarket dependency).
A3: Bridge / cross-chain messaging: V1 markets used USDC.e (USD Coin (PoS) at 0x2791bca1f2de4661ed88a30c99a7a9449aa84174 — the canonical Polygon PoS-bridged USDC). V2 replaces this with pUSD, which wraps BOTH native USDC and USDC.e per the pUSD constructor (usdc, usdce, vault) — so V2 is partially exposed to the Polygon PoS bridge in proportion to how much of pUSD's backing is USDC.e vs native USDC. The Polygon PoS bridge is canonical (Polygon's plasma/PoS bridge run by the Polygon validator set), not a third-party guardian-multisig bridge. No other chain deployment is in the address_book; this is a single-chain protocol.
A4: Nested collateral / restaking: none. CTF outcome tokens are direct ERC-1155 receipts against collateral; no further wrapping into LRT / receipt-of-receipt designs. pUSD wraps USDC/USDC.e 1:1, so V2 introduces one layer of wrapping on top of the underlying stables but no restaking chain. Slashing power: none — there are no slashable operator bonds in the Polymarket stack itself; bonds live on UMA's side (proposal bond) and on UMA validators.
A5: Fork lineage: ConditionalTokens (0x4D97...6045) is a direct deployment of Gnosis's open-source conditional-tokens-contracts repository (linked in github.com/Polymarket/contract-security as gnosis/conditional-tokens-contracts). Not silently relevant beyond that — recorded for completeness.
A6: Fallback mechanisms (all LIVE on-chain as of the inspected ABIs, status (i)): (a) UMA dispute mechanism — any address can dispute a proposed price by posting the proposalBond during the ~2hr liveness window, automatically resetting the market once and escalating to UMA DVM voters if a second dispute occurs; (b) ignorePrice sentinel — if UMA returns type(int256).min, the adapter resets the question rather than writing payouts; (c) onchain payout sanity check — _constructPayouts reverts on any resolved price other than 0, 0.5e18, or 1e18 (InvalidOOPrice), so a malformed UMA response cannot translate to a fractional or out-of-range payout; (d) admin emergencyResolve with 2-day safety period — provides a manual override path when UMA fails or returns ignorePrice indefinitely. (d) is also the centralization vector described in CONTROL.
A7: Out of scope under the rubric's A7 carve-out: Polymarket is deployed permissionlessly on Polygon PoS, which is a third-party L2/sidechain whose sequencer is not part of Polymarket's stack. Polymarket is not its own appchain.
A8: Keeper / relayer liveness: the operator who calls matchOrders on the CTFExchange (Polymarket's own off-chain matching service) is not a per-position keeper — no positions go stale or become insolvent in its absence; in the worst case trading halts while users retain full CTF rights (split/merge/redeem) directly. UMA proposers are permissionless and economically incentivized by the reward; if no proposer shows up, the market simply does not resolve, and admin emergencyResolve becomes the unblock path. There is no liquidation-bot dependency because there is no leverage or under-collateralized debt in the protocol.
A9: Governance-mutable EXTERNAL dependency surface: (i) UmaCtfAdapter.optimisticOracle and ctf are both 'immutable' Solidity variables set in the constructor — they CANNOT be swapped without redeploying the adapter, so admin cannot silently rewire to a malicious oracle. (ii) pUSD owner can addWrapper(address) and addMinter(address) to grant new external contracts the right to mint pUSD; per the pUSD ABI this is callable by owner() in a single tx with no timelock — so a new external dependency CAN be silently introduced into the V2 collateral surface (a malicious wrapper could be added that mints pUSD against fake collateral). Note: 'admin can upgrade the pUSD implementation' is a CONTROL-slice finding (admin can rug) and is intentionally not double-counted here per the A9 scope limit.

Why is this consensus tentative?

weak consensus margin

A fresh independent run can strengthen (or overturn) the verdict.

Run your own prompt Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-international
- protocol.name:              Polymarket International
- protocol.chains:            Polygon
- protocol.category:          Prediction Market
- protocol.website:           https://polymarket.com/?r=defillamareal
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               [
  {
    "chain": "Polygon",
    "address": "0xE111180000d2663C0091e4f400237545B87B996B",
    "role": "CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xe2222d279d744050d28e00520010520000310F59",
    "role": "Neg Risk CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296",
    "role": "Neg Risk Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0x4D97DCd97eC945f40cF65F87097ACe5EA0476045",
    "role": "Conditional Tokens (CTF)"
  },
  {
    "chain": "Polygon",
    "address": "0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB",
    "role": "pUSD CollateralToken (proxy)"
  },
  {
    "chain": "Polygon",
    "address": "0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f",
    "role": "pUSD CollateralToken (implementation)"
  },
  {
    "chain": "Polygon",
    "address": "0x93070a847efEf7F70739046A929D47a521F5B8ee",
    "role": "CollateralOnramp"
  },
  {
    "chain": "Polygon",
    "address": "0x2957922Eb93258b93368531d39fAcCA3B4dC5854",
    "role": "CollateralOfframp"
  },
  {
    "chain": "Polygon",
    "address": "0xebC2459Ec962869ca4c0bd1E06368272732BCb08",
    "role": "PermissionedRamp"
  },
  {
    "chain": "Polygon",
    "address": "0xAdA100Db00Ca00073811820692005400218FcE1f",
    "role": "CtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xadA2005600Dec949baf300f4C6120000bDB6eAab",
    "role": "NegRiskCtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xaacfeea03eb1561c4e67d661e40682bd20e3541b",
    "role": "Gnosis Safe Factory"
  },
  {
    "chain": "Polygon",
    "address": "0xaB45c5A4B0c941a2F231C04C3f49182e1A254052",
    "role": "Polymarket Proxy Factory"
  },
  {
    "chain": "Polygon",
    "address": "0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74",
    "role": "UMA Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0xCB1822859cEF82Cd2Eb4E6276C7916e692995130",
    "role": "UMA Optimistic Oracle"
  }
]

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
- https://defipunkd.com/address/137/0xE111180000d2663C0091e4f400237545B87B996B (CTF Exchange)
- https://defipunkd.com/address/137/0xe2222d279d744050d28e00520010520000310F59 (Neg Risk CTF Exchange)
- https://defipunkd.com/address/137/0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296 (Neg Risk Adapter)
- https://defipunkd.com/address/137/0x4D97DCd97eC945f40cF65F87097ACe5EA0476045 (Conditional Tokens (CTF))
- https://defipunkd.com/address/137/0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB (pUSD CollateralToken (proxy))
- https://defipunkd.com/address/137/0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f (pUSD CollateralToken (implementation))
- https://defipunkd.com/address/137/0x93070a847efEf7F70739046A929D47a521F5B8ee (CollateralOnramp)
- https://defipunkd.com/address/137/0x2957922Eb93258b93368531d39fAcCA3B4dC5854 (CollateralOfframp)
- https://defipunkd.com/address/137/0xebC2459Ec962869ca4c0bd1E06368272732BCb08 (PermissionedRamp)
- https://defipunkd.com/address/137/0xAdA100Db00Ca00073811820692005400218FcE1f (CtfCollateralAdapter)
- https://defipunkd.com/address/137/0xadA2005600Dec949baf300f4C6120000bDB6eAab (NegRiskCtfCollateralAdapter)
- https://defipunkd.com/address/137/0xaacfeea03eb1561c4e67d661e40682bd20e3541b (Gnosis Safe Factory)
- https://defipunkd.com/address/137/0xaB45c5A4B0c941a2F231C04C3f49182e1A254052 (Polymarket Proxy Factory)
- https://defipunkd.com/address/137/0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74 (UMA Adapter)
- https://defipunkd.com/address/137/0xCB1822859cEF82Cd2Eb4E6276C7916e692995130 (UMA Optimistic Oracle)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: AUTONOMY

Evaluate this protocol's autonomy: can a failure of anything outside its own contracts cause theft or loss of user principal, loss of unclaimed yield, or materially change the protocol's expected performance? "Autonomy" is not "has zero external touchpoints" — it is "external failures are either survivable or recoverable without user loss". This slice adapts DefiScan v1's Autonomy dimension; dependencies are one of several criteria, not the whole frame.

GUARDRAILS (read before grading):
- Category alone (Liquid Staking, Bridge, RWA Lending, Restaking, …) does NOT force a grade. A category is a hint about where to look; the grade must come from the concrete A1–A9 findings below.
- Base-chain consensus (Ethereum PoS, the chain's validator set, the canonical Deposit Contract at 0x00000000219ab540356cBB839Cbe05303d7705Fa) is the SUBSTRATE, not a dependency, for any protocol deployed on that chain. Do not list "depends on Ethereum" as a finding.
- Oracles or other integrations used by DOWNSTREAM protocols that happen to read this protocol's token (e.g. Chainlink stETH/USD consumed by Aave) are NOT this protocol's dependencies. Count only what THIS protocol's contracts call or trust on-chain. If a feed or contract appears in the protocol's docs only as reference material for third-party integrators, EXCLUDE IT ENTIRELY — do not log it as a finding even with a "peripheral" or "referenced only" caveat.
- "Upgradeable admin can change things" belongs to the CONTROL slice; only count it here when the upgrade surface lets governance silently swap an external dependency (see A9).
- Underlying-asset risk in opt-in, isolated markets is NOT autonomy-red on its own. When a protocol wraps third-party yield-bearing assets (LSTs, LRTs, ERC-4626 vaults, lending receipts, restaked tokens) into per-market silos that users explicitly choose, a failure of one underlying does NOT propagate to other markets and is risk the user opted into per-market. Record it under A4 with depth and propagation scope, but do not let it alone drive a red verdict — red requires an external dependency that cross-cuts the protocol or that the user did not opt into at deposit time. A failure mode that is "if the LRT you deposited is hacked, your principal in that LRT-backed market is impaired" is the underlying's autonomy story, not this protocol's; grade it on whether THIS protocol introduces additional dependencies on top.
- Sub-module enumeration is mandatory before grading. If the protocol ships distinct product lines or modules (e.g., a v2 core AMM plus a newer perps/funding-rate module, a lending pool plus a separate vault layer, an L1 core plus a cross-chain extension), enumerate each in findings and grade against the WORST module weighted by its share of TVS or its blast radius. A green core does not rescue an orange/red sub-module; conversely, a small red sub-module with capped TVS may bound the overall grade to orange. Name each module by its on-chain factory or router address. If you do not know whether a module exists, that is an unknowns[] entry, not silence. EXPLICIT TVS WEIGHTING: in the verdict, state each module's approximate share of total protocol TVS (use "~X%" if exact figures unavailable; check DeFiLlama or block-explorer balances on the module's main contract) and how that share informs the weighted grade. Format: "Module A holds ~X% of TVS (grade: <g>); Module B holds ~Y% (grade: <g>); weighted overall = <grade> because <reason>." If a red sub-module holds <5% of total TVS and is capped, the overall grade may be orange; if it holds >25%, the overall grade is red. Do not let qualitative reasoning substitute for the percentages — write the numbers.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- A1. External contract calls. Enumerate every external contract the core contracts call or read from (oracles, price feeds, AMM pools, lending pools, staking/deposit contracts, yield wrappers). For each, identify the address, the provider, and what user-facing function of this protocol would break or mis-price if that external contract paused, mis-reported, or behaved adversarially. Grep for "oracle", "aggregator", "getPrice", "latestAnswer", "chainlink", "pyth", "redstone" as a starting point. To verify an oracle is live and what it currently reports, hit https://defipunkd.com/api/contract/read?chainId=<id>&address=<oracle>&method=latestAnswer (or &method=latestRoundData, &method=getPrice, &method=description; use the BARE method name without parens) and cite the URL — the response includes blockNumber/blockHash and rawReturnData, which is stronger evidence than a docs page about which feed "should" be used.
- A2. Off-chain actor committees reporting INTO the protocol. Oracle committees, guardian multisigs, DAO-selected validator sets acting as protocol reporters, exit-bus signers, fraud-proof challengers. For each, record committee size, quorum, who picks the members, and what mis-reporting could do (mint, burn, finalize withdrawal, freeze). Distinguish this from governance admins (control slice). NOTE ON STAKING PROTOCOLS: validator slashing and node-operator misbehavior are properties of the base-chain substrate, NOT external dependencies, when the operator set is diversified enough that a coordinated failure caps at <5% principal loss. Count validator/operator risk under A2 ONLY if the operator set is small, non-diversified, or lacks bonding / slashing-insurance / diversification mitigations. A curated set of 30+ independent operators with documented diversification falls under the mitigated path; a 3-operator LST does not. Do not cite the protocol's own risk disclosure as evidence that operator failure = principal loss unless you also check the diversification and bond mitigations.
- A3. Bridge / cross-chain messaging dependencies. Only count bridges that carry material TVL or are required for a core user flow. For each, name the bridge operator (canonical L1↔L2, LayerZero, Wormhole, Axelar, custom multisig), the trust model (canonical, optimistic, light-client, guardian set), and what fraction of TVL or users ride on it. "wstETH exists on 15 chains" is not a finding unless material TVL sits there. Before listing any non-primary chain deployment as a dependency, verify it is still operational as of analysis_date — retired or sunset deployments (e.g., Lido-on-Terra, Lido-on-Solana) belong in unknowns[] or should be omitted, never cited as a current dependency.
- A4. Nested collateral / restaking chains. For restaking / LRT / receipt-of-receipt designs: record the depth of the collateral chain, every actor with slashing or freezing power at each level, and whether a failure N levels deep propagates to user principal here.
- A5. Fork lineage (silent check). If DeFiLlama's forkedFrom is non-empty, record it as one finding and move on. If empty, do NOT add a placeholder finding; it adds noise.
- A6. Fallback mechanisms and circuit breakers. What catches an external failure? Sanity-check contracts on oracle reports, rebase bounds, pause paths triggered by bad prices, second-opinion oracles, max-per-block throughput caps, withdrawal queues that absorb bad reports. Record which A1–A4 risks are mitigated by which fallback, and which are unmitigated. For EACH fallback you cite, state its activation status explicitly: (i) LIVE and enforcing on-chain today, (ii) DEPLOYED but not yet wired / activated (e.g., interface exists but the address is zero or the role is unassigned), or (iii) DOCUMENTED / PROPOSED only (forum post, LIP draft, audit pending). Only (i) counts as mitigation for the grade. A fallback in state (ii) or (iii) should be noted but must not reduce the risk in your steel-man or verdict. If you cannot determine activation status, add an unknowns[] entry rather than assume it is live.
- A7. Sequencer / L1-liveness dependency BEYOND the base-chain substrate. SCOPE — sequencer risk only counts here when the protocol IS its own L2/L3 appchain or app-rollup, where the sequencer is part of the protocol's own stack and a freeze is a protocol-level outage. A protocol permissionlessly deployed on a third-party L2 inherits that L2's sequencer as substrate, not an A7 dependency. Record the sequencer/DA trust model when A7 applies.
- A8. Keeper / relayer / off-chain bot liveness. Protocols that need permissionless-but-necessary off-chain actors (liquidation bots, auto-compounders, deposit relayers, intent solvers). Record whether the role is permissionless, what degrades if nobody runs it (yield paused, bad debt accumulates, positions go stale), and whether the failure mode is graceful or catastrophic.
- A9. Governance-mutable dependency surface. Can an admin or DAO action silently INTRODUCE a NEW EXTERNAL dependency — swap the oracle address to a different provider, register a new staking module that calls an untrusted contract, add a new bridge, route SY through a new external vault — without an exit window for users? Check the upgrade / router / module-registry contracts. Answer: which EXTERNAL dependencies are governance-mutable, who holds that power, and whether there is a timelock or exit window. SCOPE LIMIT — read carefully: A9 is about the *external dependency surface*, not the upgrade surface in general. "The proxyAdmin / EOA can upgrade the router implementation to arbitrary bytecode" is a CONTROL-slice finding (admin can rug), NOT an autonomy-A9 finding. A9 fires only when the upgrade specifically swaps out or adds a contract that THIS protocol calls or trusts (e.g., changing the oracle address from Chainlink to a malicious feed, registering a new SY adapter that points to a third-party vault, redirecting a bridge endpoint). If the only finding is "admin can change implementation," do not log it under A9 and do not let it drive the autonomy grade — note it under control instead. The autonomy-relevant version of the same upgrade key is "admin can swap [specific external address X] without timelock"; that requires identifying the specific external dependency that becomes mutable.

STEEL-MAN (per Hard Rule 13): write one-sentence strongest arguments for red, orange, and green using the A1–A9 findings.

IMPACTED TVS ESTIMATE: the headline MUST include a rough impacted-TVS figure — the fraction of protocol TVS that could be lost or frozen if the worst-unmitigated dependency you identified failed. Use "~X%" if exact numbers are unavailable, "<1%" for de minimis, "unclear" only if A1–A9 left the question genuinely open (in which case grade=unknown is usually correct). Do NOT substitute qualitative phrases like "significant" — give a number or bracket.

GRADE ANCHORS (mapped to DefiScan v1 stages):
- green = Stage 2 equivalent. Failure of any external dependency cannot cause loss of user principal or unclaimed yield. Either there are no material external dependencies, or every critical one has a documented fallback (A6) that keeps users whole. Governance cannot silently introduce new dependencies without an exit window (A9). Impacted TVS under any single-dependency failure: effectively 0.
- orange = Stage 1 equivalent. Failure of some external dependency can cause loss of unclaimed yield, or can materially change expected performance (pause withdrawals, freeze positions, degrade price quality), but cannot cause loss of principal. Committee-based oracles with sanity checks, canonical-only bridges, fallback paths that exist but are incomplete, or governance-mutable dependencies protected by a ≥7-day timelock. Impacted TVS is bounded and recoverable.
- red = Stage 0 equivalent. Failure of an external dependency CAN cause theft or loss of principal. Examples: single-provider oracle with no sanity check or fallback, material TVL on a non-canonical bridge with a guardian multisig, governance can hot-swap oracles or add staking modules with no timelock or exit window, unmitigated keeper-liveness dependency where positions become insolvent if bots stop. Impacted TVS is material.
- unknown = checklist incomplete after inspecting source + verified contracts. Prefer unknown over guessing when A1/A6 could not be reconstructed. RESERVE unknown for cases where the CORE ARCHITECTURE itself is unverifiable — not for cases where you merely cannot enumerate every per-market dependency in a multi-market protocol. If the core router/factory/oracle architecture is verifiable on-chain and you can determine whether the core requires external dependencies, grade the architecture even when an exhaustive per-market external-dependency census is infeasible. Acknowledge the per-market gap in unknowns[] but still issue a grade. Refusing to grade a multi-market protocol because you cannot list every SY/vault/market is over-use of unknown; grade the architecture and say so.

PROMPT-META CHECK (per Hard Rule 17): before finalizing, verify the verdict cites concrete contract addresses, docs, or code — not the rubric itself. If your verdict says "the protocol belongs to a category the rubric marks red", rewrite it with the A1–A9 finding that actually justifies the grade, or drop to grade=unknown.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "autonomy",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Sources claude-opus-4-7 url ↗ gpt-5.5-thinking url ↗ grok-3 url ↗ View raw submissions ↗

Open Access tentative 3/3 models agree AI-only 3/3 with chat share link

Contracts admit users unconditionally; CTF deposit/exit and order signing are permissionless; multiple independent access paths exist; frontend ToS §2.1.4 and /api/geoblock are publisher policies on the official UI only

Verdict

Choosing green because the rubric explicitly states: 'when contracts are fully permissionless AND any A3b independent path exists, the default grade is green regardless of frontend ToS or A3-active enforcement on the official UI' — A1, A4, A5 establish the contracts admit users unconditionally; A3b shows multiple independent paths (Polymarket-published CLI, CLOB SDKs, direct CTF calls via any wallet); the operator-gated matching is a liveness concern that the rubric explicitly defers to dependencies; and the orange steel-man relies on operator capture for one specific user action (orderbook trading) while ignoring that mint/exit/transfer are operator-free.

Steelman argument

Steelman argument User entry (splitPosition), exit (redeemPositions, mergePositions), and order-signing are all unconditional on-chain actions on contracts with no on-chain blocklist; Polymarket itself publishes a CLI and TypeScript/Python SDKs that interact directly with the contracts and CLOB API without the official frontend, satisfying the rubric's A3b independent-path test, so per the default-grade guidance the grade is green regardless of frontend ToS / geoblock policy on the official UI.

Evidence (7)

A1: No on-chain whitelist / KYC modifier on user-facing entry/exit. ConditionalTokens (0x4D97...6045) has no onlyWhitelisted / onlyRole / isAccredited / isKYCed guards on splitPosition, mergePositions, redeemPositions, safeTransferFrom, or safeBatchTransferFrom (entire ABI inspected). CTFExchange V2 (0xE111...996B) likewise gates only operator/admin-side functions; user-side order signing is permissionless — orders are signed off-chain and only land on-chain via the operator. isUserPaused exists but is a per-user emergency tool with userPauseBlockInterval, not an allowlist.
A2: Off-chain operators in the admission path: CTFExchange V2 matchOrders is gated by NotOperator / isOperator — the Polymarket-run operator is the sole settler of matched orders. Per the rubric: order PLACEMENT is unconditional (any address can sign and broadcast an Order tuple), only downstream settlement requires the operator. By the rubric's explicit guidance, this is an admission-permissionless function with a liveness dependency, and the liveness weight defers to the dependencies/autonomy slice (see AUTONOMY A8). Direct CTF user actions (splitPosition / mergePositions / redeemPositions / transfers) require no operator at all.
A3: Frontend restrictions on polymarket.com (recorded as context, not grade driver): A3-active enforcement is present — there is a documented runtime geoblock endpoint at /api/geoblock returning {blocked, ip, country, region}, and the Polymarket help center lists ~33 fully or partially restricted jurisdictions (US, France, Belgium, Singapore, Portugal, Hungary, Switzerland, Poland, Ontario, Italy, Germany, etc.). A3-passive ToS clauses are also present — the Polymarket help-center page on Geographic Restrictions states the protocol's ToS Section 2.1.4 prohibits use of VPNs or similar tools to bypass geographic restrictions; the verbatim text could not be extracted from polymarket.com/tos because the page is client-side rendered and returned only the header / footer chrome on direct HTTP fetch (see unknowns).
A3b: Independent access paths NOT requiring the official polymarket.com frontend: (i) github.com/Polymarket/polymarket-cli — a Polymarket-published CLI that handles direct CTF operations and CLOB orders without the frontend ('polymarket ctf redeem', 'polymarket ctf merge', 'polymarket clob create-order'); (ii) github.com/Polymarket/clob-client-v2 and py-clob-client-v2 — TypeScript and Python SDKs for direct CLOB API access; (iii) github.com/Polymarket/magic-proxy-builder-example — third-party-style Next.js app demonstrating non-frontend access to a user's Polymarket proxy wallet; (iv) any Polygon wallet or block explorer can call redeemPositions / mergePositions on the immutable CTF directly. The contracts can be reached without the publisher's cooperation.
A4: No contract-level OFAC / sanctions screening was visible on any inspected ABI (ConditionalTokens, CTFExchange V2, UmaCtfAdapter, pUSD CollateralToken) — no isOnSanctionsList / oracleScreening / blocklist mapping. Compliance enforcement is frontend-only per A3.
A5: Read access is fully public (Polygon RPC + verified contract source via Polygonscan / defipunkd). Write access to user-side CTF functions is unrestricted; write access to admin functions is role-gated; the CLOB matching write is operator-gated — see A2.
A6: ToS / Legal: Polymarket help-center confirms ToS Section 2.1.4 prohibits VPN use, and the polymarket.com footer states 'Polymarket operates globally through separate legal entities. Polymarket US is operated by QCX LLC d/b/a Polymarket US, a CFTC-regulated Designated Contract Market. This international platform is not regulated by the CFTC and operates independently.' Verbatim Section 2.1.4 text was not extractable from the SPA-rendered ToS page in this run; the existence of the clause is corroborated by the official help-center article (help.polymarket.com/en/articles/13364163-geographic-restrictions) which states verbatim: 'Polymarket strictly prohibits the use of VPNs or similar tools to bypass geographic restrictions. Such actions are considered violations of the platform's Terms of Service (Section 2.1.4).'

Why is this consensus tentative?

weak consensus margin

A fresh independent run can strengthen (or overturn) the verdict.

Run your own prompt Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-international
- protocol.name:              Polymarket International
- protocol.chains:            Polygon
- protocol.category:          Prediction Market
- protocol.website:           https://polymarket.com/?r=defillamareal
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               [
  {
    "chain": "Polygon",
    "address": "0xE111180000d2663C0091e4f400237545B87B996B",
    "role": "CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xe2222d279d744050d28e00520010520000310F59",
    "role": "Neg Risk CTF Exchange"
  },
  {
    "chain": "Polygon",
    "address": "0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296",
    "role": "Neg Risk Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0x4D97DCd97eC945f40cF65F87097ACe5EA0476045",
    "role": "Conditional Tokens (CTF)"
  },
  {
    "chain": "Polygon",
    "address": "0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB",
    "role": "pUSD CollateralToken (proxy)"
  },
  {
    "chain": "Polygon",
    "address": "0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f",
    "role": "pUSD CollateralToken (implementation)"
  },
  {
    "chain": "Polygon",
    "address": "0x93070a847efEf7F70739046A929D47a521F5B8ee",
    "role": "CollateralOnramp"
  },
  {
    "chain": "Polygon",
    "address": "0x2957922Eb93258b93368531d39fAcCA3B4dC5854",
    "role": "CollateralOfframp"
  },
  {
    "chain": "Polygon",
    "address": "0xebC2459Ec962869ca4c0bd1E06368272732BCb08",
    "role": "PermissionedRamp"
  },
  {
    "chain": "Polygon",
    "address": "0xAdA100Db00Ca00073811820692005400218FcE1f",
    "role": "CtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xadA2005600Dec949baf300f4C6120000bDB6eAab",
    "role": "NegRiskCtfCollateralAdapter"
  },
  {
    "chain": "Polygon",
    "address": "0xaacfeea03eb1561c4e67d661e40682bd20e3541b",
    "role": "Gnosis Safe Factory"
  },
  {
    "chain": "Polygon",
    "address": "0xaB45c5A4B0c941a2F231C04C3f49182e1A254052",
    "role": "Polymarket Proxy Factory"
  },
  {
    "chain": "Polygon",
    "address": "0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74",
    "role": "UMA Adapter"
  },
  {
    "chain": "Polygon",
    "address": "0xCB1822859cEF82Cd2Eb4E6276C7916e692995130",
    "role": "UMA Optimistic Oracle"
  }
]

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
- https://defipunkd.com/address/137/0xE111180000d2663C0091e4f400237545B87B996B (CTF Exchange)
- https://defipunkd.com/address/137/0xe2222d279d744050d28e00520010520000310F59 (Neg Risk CTF Exchange)
- https://defipunkd.com/address/137/0xd91E80cF2E7be2e162c6513ceD06f1dD0dA35296 (Neg Risk Adapter)
- https://defipunkd.com/address/137/0x4D97DCd97eC945f40cF65F87097ACe5EA0476045 (Conditional Tokens (CTF))
- https://defipunkd.com/address/137/0xC011a7E12a19f7B1f670d46F03B03f3342E82DFB (pUSD CollateralToken (proxy))
- https://defipunkd.com/address/137/0x6bBCef9f7ef3B6C592c99e0f206a0DE94Ad0925f (pUSD CollateralToken (implementation))
- https://defipunkd.com/address/137/0x93070a847efEf7F70739046A929D47a521F5B8ee (CollateralOnramp)
- https://defipunkd.com/address/137/0x2957922Eb93258b93368531d39fAcCA3B4dC5854 (CollateralOfframp)
- https://defipunkd.com/address/137/0xebC2459Ec962869ca4c0bd1E06368272732BCb08 (PermissionedRamp)
- https://defipunkd.com/address/137/0xAdA100Db00Ca00073811820692005400218FcE1f (CtfCollateralAdapter)
- https://defipunkd.com/address/137/0xadA2005600Dec949baf300f4C6120000bDB6eAab (NegRiskCtfCollateralAdapter)
- https://defipunkd.com/address/137/0xaacfeea03eb1561c4e67d661e40682bd20e3541b (Gnosis Safe Factory)
- https://defipunkd.com/address/137/0xaB45c5A4B0c941a2F231C04C3f49182e1A254052 (Polymarket Proxy Factory)
- https://defipunkd.com/address/137/0x6A9D222616C90FcA5754cd1333cFD9b7fb6a4F74 (UMA Adapter)
- https://defipunkd.com/address/137/0xCB1822859cEF82Cd2Eb4E6276C7916e692995130 (UMA Optimistic Oracle)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: OPEN-ACCESS

Evaluate who is allowed to use the protocol and whether any of that permission is granted off-chain.

Scope: this slice is about ADMISSION — who can enter, exit, or transact. Operator LIVENESS (what breaks if keepers/oracles go offline) is assessed in the dependencies slice and is out of scope for the grade here. You may note operator dependencies as context, but do not let "the protocol halts if operator X disappears" drive the access grade on its own; that belongs in dependencies. Source verification / contract verification on block explorers is assessed in the verifiability slice and is out of scope here — do NOT let "contract is unverified" drive the access grade.

Framing: the smart contracts are the access layer; frontends are UX. A permissionless contract is reachable by any client (SDK, third-party UI, aggregator, wallet integration). Frontend ToS, IP geo-blocking, and wallet screening are publisher policies on one specific client — they are reported as context but do NOT determine the grade. The grade hinges on (1) what the contract itself permits, and (2) whether the protocol is practically reachable without the official publisher's cooperation.

Meta-check before finalizing: if your verdict cites phrases from this prompt as evidence ("the protocol meets the 'credible alternatives' condition", "this fits the 'documented fallback' rule"), redo the verdict. The prompt describes the rubric; evidence must come from the protocol. A verdict should cite what the protocol does, not what the rubric says.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- A1. Whitelist / allowlist modifiers in user-facing entry points. Grep for "onlyWhitelisted", "onlyRole", "allowlist", "isAccredited", "isKYCed". Note which functions are gated and who can add/remove from the list.
- A2. Off-chain operators in the admission path: keepers, sequencers, privileged relayers, oracle posters whose approval is required to admit a user action (not just to keep the protocol live). For each, identify whether the role is held by a single operator, a permissioned committee, or is permissionless. Enumerate per user-facing function class (deposit vs withdraw-request vs claim-finalized vs transfer) which ones require operator approval to be admitted, and which ones admit users unconditionally. A function whose placement is unconditional but whose downstream settlement depends on an operator is an admission-permissionless function — flag the liveness dependency as context and defer its grading weight to the dependencies slice.
- A3. Frontend restrictions on the official interface — record as context, not as a grade lever. Distinguish:
    - A3-passive: boilerplate ToS clauses (sanctions attestation, restricted-territory self-certification, VPN-circumvention prohibition, "comply with applicable law" eligibility, age of majority).
    - A3-active: runtime enforcement — IP-based geo-blocking, wallet-address screening against a sanctions oracle (Chainalysis, TRM, Elliptic), KYC wall, rendering-blocking jurisdiction banner.
  Record findings under the correct tier. Quote ToS text or banner text in evidence[].shows. These findings populate the headline and rationale but do NOT move the grade by themselves; the grade is set by A1, A2, and the A3b path check below.
- A3b. Independent access paths (the operative grade input). Enumerate paths that do not require the official publisher's cooperation:
    - Published SDK / library / CLI for direct contract interaction.
    - Third-party frontends operated by separate legal entities.
    - Wallet-integrated access (MetaMask Swaps, Safe apps, etc.).
    - DEX / lending / yield aggregators that route through the contracts.
  Record at least one concrete link per path that exists. The protocol does NOT have to self-document these — the test is existence, not UX cost. An A3b-i redistribution of the official UI bound by the same ToS does NOT count as an independent path.
- A4. Sanctions / compliance tooling at the contract level: does the protocol check addresses against OFAC lists or similar on-chain blocklists in the contract itself? (Frontend-only screening belongs in A3.)
- A5. Differentiate read access vs write access: many protocols are read-permissionless (anyone can view state) but write-gated (only certain addresses can deposit/borrow). Record both.
- A6. ToS / Legal links: locate them on the website and produce a VERBATIM quote of any jurisdictional, sanctions, or eligibility clause in evidence[].shows. If you cannot extract the clause text verbatim (SPA render failure, paywall, dead link, etc.), do NOT paraphrase or infer from general knowledge — record the ToS URL in unknowns[] with the reason extraction failed. Assertions about ToS content without a verbatim quote will be downweighted by reviewers.

Then write the steel-man section per Hard Rule 11.

Grade rules (admission-focused; liveness concerns belong in dependencies; source verification belongs in verifiability):
- green   = no contract-level whitelist/KYC on user entry/exit; no operator approval required to admit a user action; AND at least one independent A3b path exists (published SDK, third-party frontend, wallet integration, or aggregator routing). Frontend ToS posture and A3-active enforcement on the official UI do NOT block green when contracts are permissionless and an independent path exists — they are reported as context.
- orange  = contracts admit users unconditionally, BUT the protocol is operationally captured by the official publisher: no published SDK, no third-party frontend, no wallet integration, no aggregator routing. The contract is theoretically open but practically reachable only through the official UI. Also applies when admission requires approval from a permissioned committee that is governance-managed with a documented replacement procedure.
- red     = contract-level whitelist / KYC on user entry/exit, OR admission of a core user action requires approval from a single privileged operator or a small committee with no documented replacement procedure, OR enforces an on-chain blocklist updatable by a single party.
- unknown = checklist incomplete after checking the sources above.

Default-grade guidance: when contracts are fully permissionless AND any A3b independent path exists, the default grade is green regardless of frontend ToS or A3-active enforcement on the official UI. Frontend geo-blocking, sanctions-oracle wallet screening, and ToS sanctions clauses are publisher policies on one client and are reported in findings/headline as context, not as grade levers. To grade orange on operational-capture grounds, the auditor must affirmatively show that ALL independent paths are absent or also gated.

Guideline on committees: where admission depends on a multi-operator committee, the relevant axes are (a) set size, (b) whether replacement/rotation is governed on-chain, (c) whether the replacement procedure is publicly documented. A large set with on-chain governance replacement should not be graded as a single-party operator even if rotation is not instantaneous. A small set with informal replacement should be treated as a single-party operator.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "open-access",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Sources claude-opus-4-7 url ↗ gpt-5.5-thinking url ↗ grok-3 url ↗ View raw submissions ↗

Stage

Preview of the Phase-3 maturity framework. DeFiPunk'd will adopt DeFiScan v2's stages verbatim; the section is rendered below in its intended shape so the structure is visible today.

Polymarket International has not yet been assessed under the DeFiScan v2 stage framework.

The walkaway test is the central criterion. Once stages land, protocols reach Stage 1 only if users can exit in the presence of malicious operators even when the emergency council disappears.

Scope of assessment

Stages are assessed per-protocol against DeFiScan v2's criteria: governance structure, upgradeability path, timelock durations, emergency-council scope, and the walkaway test. The analysis depends on onchain discovery (roles, owners, timelocks) and deeper review of deployed contracts — neither of which DeFiPunk'd automates at Phase 0.

Stage 0 requirements pending

Governance is largely off-chain, contracts are upgradeable with short or no timelock, and the protocol depends on a multisig or team with full discretion. At Phase 0 DeFiPunk'd does not automatically evaluate these; the assessment lands with crawler-based onchain discovery.

Stage 1 requirements pending

Users can exit or opt out on their own terms even if the team disappears. Upgrades run through a meaningful timelock with an emergency security council clearly scoped. The walkaway test is the headline criterion.

Stage 2 requirements pending

Protocol is fully permissionless and immutable, or upgrades require a supermajority of token holders with a long timelock and no emergency override. This is the terminal stage of the DeFiScan v2 framework.

Learn more about DeFiScan v2 stages →

Stages are an opinionated assessment of maturity, not a rating of security or safety. A protocol can sit at Stage 2 and still carry substantial technical or economic risk; the framework exists to incentivize decentralization, not to rank protocols.

Contract surface

Every contract in scope for this protocol — pooled from DeFiLlama's TVL adapter (mechanical) and DEFI@home discovery submissions (LLM-curated). Verified-source flags come from Etherscan + Sourcify; owner / multisig metadata is read on-chain when available. Reviewer audit context, not a slice score. A lending protocol's adapter set will list third-party collateral tokens alongside its own contracts; attribution is the grader's job.

114addresses
43verified source
8proxies
16of 32 owners are Safes

TVL adapter pinned at 683d369. Sourcecode fetched 2026-05-06. Control fetched 2026-05-14.

Mainnet only


arbitrum	AnyswapV5ERC20	`0xfea7…6c2a`	TVL	✓	—	`0xf46b…5aea`	5/10 Safe
boba	BUSD	`0x461d…4eb5`	TVL	—	—	—	—
covalentGetTokens	null	`0x0000…0000`	TVL	—	—	—	—
dogechain	BUSD	`0x3327…41ff`	TVL	—	—	—	—
dogechain	MATIC	`0xdc42…1f98`	TVL	—	—	—	—
ethereum	Dai	`0x6b17…1d0f`	TVL	✓	—	—	—
ethereum	LobstersNft	`0x0262…f042`	TVL	✓	—	`0x5570…1e6f`	7/19 Safe
ethereum	CoolCats	`0x1a92…050c`	TVL	✓	—	`0xd588…19bf`	3/5 Safe
ethereum	Toadz	`0x1cb1…49c6`	TVL	✓	—	`0x794b…9672`	2/4 Safe
ethereum	Moonbirds	`0x2358…a68b`	TVL	✓	—	`0x80d1…d044`	2/4 Safe
ethereum	Beanz	`0x306b…f949`	TVL	✓	—	`0x2ae6…60aa`	3/6 Safe
ethereum	Land	`0x34d8…e258`	TVL	✓	—	`0x1633…0053`	2/6 Safe
ethereum	TransparentUpgradeableProxy	`0x39ee…21b6`	TVL	✓	proxy	`0x1c59…9417`	—
ethereum	OniForce	`0x3bf2…5e9d`	TVL	✓	—	`0x615d…00f0`	—
ethereum	CDBS3	`0x4206…1cdb`	TVL	✓	—	`0x68bd…a63b`	2/3 Safe
ethereum	CloneX	`0x49cf…a28b`	TVL	✓	—	`0x12ea…f0af`	—
ethereum	ForgottenRunesWizardsCult	`0x521f…6f42`	TVL	✓	—	`0xd584…4a51`	—
ethereum	Miladys	`0x5af0…25a5`	TVL	✓	—	`0x54f8…28cb`	—
ethereum	TransparentUpgradeableProxy	`0x5cc5…0c38`	TVL	✓	proxy	`0x96ef…fff1`	—
ethereum	MutantApeYachtClub	`0x60e4…a7c6`	TVL	✓	—	`0xa858…2ef1`	3/9 Safe
ethereum	TransparentUpgradeableProxy	`0x7692…44cc`	TVL	✓	proxy	`0x1c59…9417`	—
ethereum	ERC1967Proxy	`0x790b…8371`	TVL	✓	proxy	—	—
ethereum	Meebits	`0x7bd2…6bc7`	TVL	✓	—	—	—
ethereum	ERC1967Proxy	`0x8821…d280`	TVL	✓	proxy	`0x28b2…41f5`	2/2 Safe
ethereum	CyberBrokers	`0x8928…ca85`	TVL	✓	—	`0x070c…86de`	—
ethereum	Doodles	`0x8a90…992e`	TVL	✓	—	`0x9d86…3ba8`	2/4 Safe
ethereum	NounsToken	`0x9c8f…dc03`	TVL	✓	—	`0xb1a3…ef71`	—
ethereum	RightwayToken	`0xa3ae…beeb`	TVL	✓	—	—	—
ethereum	EtherRockERC721	`0xa3f5…fc02`	TVL	✓	—	—	—
ethereum	WrappedPunk	`0xb7f7…13f6`	TVL	✓	—	—	—
ethereum	BoredApeKennelClub	`0xba30…5623`	TVL	✓	—	`0xa858…2ef1`	3/9 Safe
ethereum	BoredApeYachtClub	`0xbc4c…f13d`	TVL	✓	—	—	—
ethereum	goblintownNFT	`0xbce3…307e`	TVL	✓	—	`0x62ac…fa0f`	—
ethereum	PudgyPenguins	`0xbd35…2cf8`	TVL	✓	—	`0xf54c…4f1d`	—
ethereum	DigiDaigaku	`0xd125…94a9`	TVL	✓	—	`0x5a8c…586d`	2/3 Safe
ethereum	ERC1967Proxy	`0xe012…5903`	TVL	✓	proxy	—	—
ethereum	WorldOfWomen	`0xe785…5330`	TVL	✓	—	`0xc9b6…bdb1`	—
ethereum	Azuki	`0xed5a…c544`	TVL	✓	—	`0x2ae6…60aa`	3/6 Safe
ethereum	LANDProxy	`0xf87e…5d4d`	TVL	✓	proxy	`0xfe95…af4a`	—
ethereum	FantomToken	`0x4e15…7870`	TVL	✓	—	`0xb5c4…3f70`	2/4 Safe
ethereum	CvxLockerV2	`0x72a1…b86e`	TVL	✓	—	`0xa3c5…e2fb`	3/5 Safe
eulerTokens	eulerTokens	`0x1b80…dc1d`	TVL	—	—	—	—
eulerTokens	eulerTokens	`0x3c66…62d0`	TVL	—	—	—	—
eulerTokens	eulerTokens	`0x4169…d264`	TVL	—	—	—	—
eulerTokens	eulerTokens	`0x4d19…85d2`	TVL	—	—	—	—
eulerTokens	eulerTokens	`0x5484…054e`	TVL	—	—	—	—
eulerTokens	eulerTokens	`0x6089…c527`	TVL	—	—	—	—
eulerTokens	eulerTokens	`0x64ad…ee82`	TVL	—	—	—	—
eulerTokens	eulerTokens	`0xbd1b…d593`	TVL	—	—	—	—
eulerTokens	eulerTokens	`0xe025…d9dc`	TVL	—	—	—	—
eulerTokens	eulerTokens	`0xeb91…a716`	TVL	—	—	—	—
fantom	anyUSDC	`0x95bf…d605`	TVL	✗	—	—	—
fantom	DAI	`0x8d11…bf3e`	TVL	✗	—	—	—
fantom	fUSDT	`0x049d…3c7a`	TVL	✗	—	—	—
fantom	MIM	`0x82f0…29c1`	TVL	✗	—	—	—
fantom	nICE	`0x7f62…e443`	TVL	✗	—	—	—
fantom	USDC	`0x0406…5b75`	TVL	✗	—	—	—
genericUnwrapCvx	target	`0xf403…ae31`	TVL	—	—	—	—
harmony	AVAX	`0xb12c…1358`	TVL	—	—	—	—
kcc	DAI	`0xc9ba…2055`	TVL	—	—	—	—
kcc	WBTC	`0x218c…a4c0`	TVL	—	—	—	—
moonriver	AnyswapV5ERC20	`0x639a…2c5c`	TVL	✓	—	`0x10c6…7e23`	—
moonriver	AnyswapV5ERC20	`0xe3f5…ad7d`	TVL	✓	—	`0x10c6…7e23`	—
moonriver	AnyswapV5ERC20	`0xb44a…663c`	TVL	✓	—	`0x10c6…7e23`	—
nullAddress	null	`0x0000…0000`	TVL	—	—	—	—
PANCAKE_NFT_ADDRESS	PANCAKE_NFT_ADDRESS	`0x46a1…4364`	TVL	—	—	—	—
polygon	WrappedCollateral	`0x3a3b…02e2`	TVL	✓	—	—	—
polygon	ConditionalTokens	`0x4d97…6045`	TVL + disc	✓	—	—	—
polygon	UChildERC20Proxy	`0x2791…4174`	TVL	✓	proxy	—	—
Polygon	CollateralOfframp	`0x2957…5854`	discovery	—	—	—	—
Polygon	CollateralOnramp	`0x9307…b8ee`	discovery	—	—	—	—
Polygon	CTF Exchange	`0xe111…996b`	discovery	—	—	—	—
Polygon	CtfCollateralAdapter	`0xada1…ce1f`	discovery	—	—	—	—
Polygon	Gnosis Safe Factory	`0xaacf…541b`	discovery	—	—	—	multisig
Polygon	Neg Risk Adapter	`0xd91e…5296`	discovery	—	—	—	—
Polygon	Neg Risk CTF Exchange	`0xe222…0f59`	discovery	—	—	—	—
Polygon	NegRiskCtfCollateralAdapter	`0xada2…eaab`	discovery	—	—	—	—
Polygon	PermissionedRamp	`0xebc2…cb08`	discovery	—	—	—	—
Polygon	Polymarket Proxy Factory	`0xab45…4052`	discovery	—	—	—	factory
Polygon	pUSD CollateralToken (implementation)	`0x6bbc…925f`	discovery	—	—	—	—
Polygon	pUSD CollateralToken (proxy)	`0xc011…2dfb`	discovery	—	—	—	—
Polygon	UMA Adapter	`0x6a9d…4f74`	discovery	—	—	—	—
Polygon	UMA Optimistic Oracle	`0xcb18…5130`	discovery	—	—	—	oracle
shiden	BUSD	`0x65e6…d97a`	TVL	—	—	—	—
shiden	ETH	`0x7652…9c61`	TVL	—	—	—	—
shiden	JPYC	`0x735a…7b0f`	TVL	—	—	—	—
sumTokens	null	`0x0000…0000`	TVL	—	—	—	—
sumTokens2	null	`0x0000…0000`	TVL	—	—	—	—
syscoin	ETH	`0x7c59…227d`	TVL	—	—	—	—
syscoin	USDC	`0x2bf9…c45c`	TVL	—	—	—	—
syscoin	USDT	`0x922d…12e1`	TVL	—	—	—	—
telos	ETH	`0xfa93…a40f`	TVL	—	—	—	—
telos	USDC	`0x818e…dc0b`	TVL	—	—	—	—
telos	USDT	`0xefae…0d73`	TVL	—	—	—	—
telos	WBTC	`0xf390…cbc2`	TVL	—	—	—	—
unwrapMakerPositions	CDP_MANAGER	`0x5ef3…5e39`	TVL	—	—	—	—
unwrapMakerPositions	ILK_REGISTRY	`0x5a46…0f87`	TVL	—	—	—	—
unwrapMakerPositions	PROXY_REGISTRY	`0x4678…3fe4`	TVL	—	—	—	—
unwrapUniswapV3NFT	factory	`0x71b0…6127`	TVL	—	—	—	factory
unwrapUniswapV3NFT	unwrapUniswapV3NFT	`0xa08a…5aab`	TVL	—	—	—	—
unwrapUniswapV4NFTs	nftAddress	`0x3c3e…1017`	TVL	—	—	—	—
unwrapUniswapV4NFTs	nftAddress	`0x4529…17bf`	TVL	—	—	—	—
unwrapUniswapV4NFTs	nftAddress	`0x5b7e…4016`	TVL	—	—	—	—
unwrapUniswapV4NFTs	nftAddress	`0x7a4a…f95b`	TVL	—	—	—	—
unwrapUniswapV4NFTs	nftAddress	`0x7c5f…9bdc`	TVL	—	—	—	—
unwrapUniswapV4NFTs	nftAddress	`0xbd21…ee9e`	TVL	—	—	—	—
unwrapUniswapV4NFTs	nftAddress	`0xd88f…d869`	TVL	—	—	—	—
unwrapUniswapV4NFTs	stateViewer	`0x76fd…9990`	TVL	—	—	—	—
unwrapUniswapV4NFTs	stateViewer	`0x7739…9d64`	TVL	—	—	—	—
unwrapUniswapV4NFTs	stateViewer	`0x7ffe…7227`	TVL	—	—	—	—
unwrapUniswapV4NFTs	stateViewer	`0x86e8…e8f2`	TVL	—	—	—	—
unwrapUniswapV4NFTs	stateViewer	`0xa3c0…7a71`	TVL	—	—	—	—
unwrapUniswapV4NFTs	stateViewer	`0xc18a…ecdb`	TVL	—	—	—	—
unwrapUniswapV4NFTs	stateViewer	`0xd13d…e0c4`	TVL	—	—	—	—

TVL —

Type Prediction Market

Chains —

View on DeFiLlama ↗

Control Exit Autonomy Open Access Verifiable

Verifiability tentative No public repo or audits
Control unknown Not yet assessed
Ability to exit unknown Not yet assessed
Autonomy unknown No Phase-0 autonomy signal
Open Access unknown Not yet assessed

Control criteria

Upgradeability — Bug bounty cantina.xyz Governance forum — Docs —

About

Polymarket US is a prediction market protocol.

Risk analysis

One card per dimension, sorted by severity. Only Verifiability and Autonomy carry automated signals in Phase 0. See methodology for scope.

Audit a dimension yourself · DEFI@home Contribute an LLM-run assessment — any model, any dimension. Three agreeing runs merge automatically into the public record.

Address discovery 0 addresses on file · 0 runs ⚑ Run first Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-us
- protocol.name:              Polymarket US
- protocol.chains:            (none recorded)
- protocol.category:          Prediction Market
- protocol.website:           https://polymarketexchange.com/
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               null

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
(no addresses pinned in this run — discover candidates from fetched website / GitHub / audit / explorer pages, record discovered addresses in evidence[] and protocol_metadata.admin_addresses, and put any reads you couldn't perform in unknowns[]. The next assessment will inherit your discoveries.)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: DISCOVERY

You are a cataloguer, not a judge. Your job is to surface every contract address that could plausibly belong to this protocol's control or fund-holding surface, each backed by a citation. `grade` is ALWAYS `"unknown"` for discovery submissions — there is no green/orange/red rubric here. The five evaluation slices that run after you (control, ability-to-exit, autonomy, open-access, verifiability) consume your output via the addressBook ratchet — every address you record becomes a pre-built surfacer URL on the next run; every address you miss costs them a tool call.

Width beats depth. A `role: "other"` entry with one cited URL beats omitting it. Downstream slices will discard out-of-scope entries; they cannot rediscover what you fail to enumerate without paying the same cost again.

(Step 0 capability probe lives in the preamble — those rules apply here.)

### MANDATORY INSPECTION CHECKLIST (every D-code below must appear in evidence[] OR unknowns[])

- **D1. Block-explorer name-tag search per chain.** For each chain in `protocol.chains`, search the canonical block explorer for the protocol's name tag — `https://etherscan.io/searchHandler?term=<query>` and the per-chain explorers (basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network). When direct fetch is blocked, use `site:<explorer> <protocol_name>` via search grounding. Record every address that surfaces with the protocol's tag, plus neighbouring "Token Contract" / "Multisig" / "Timelock" labels.

- **D2. Official deployments doc.** From `protocol.website` and the docs site, locate the canonical "Deployed contracts" / "Addresses" / "Contracts" / "Deployments" page (often at `/docs/deployments`, `/docs/addresses`, `/dashboard/contracts`). Cite the URL, record every address listed with its named role, and set `protocol_metadata.deployed_contracts_doc` to this URL.

- **D3. Audit PDFs.** From `protocol.audit_links` (and any audits surfaced by D2), open each. Most reports include a "Scope" / "Contracts in scope" address table in the first 5 pages. Extract every in-scope address with its labelled role. If the audit predates the current deployment, record the addresses anyway with role suffixed `(audit-era)` so downstream slices know to re-verify.

- **D4. GitHub deployment artifacts.** From `protocol.github`, walk the repo at a pinned commit SHA looking for: Foundry `broadcast/<script>/<chainId>/run-latest.json` (`transactions[].contractAddress` per chainId); hardhat-deploy `deployments/<network>/<Contract>.json` (`address` field); manual indexes (`deployments.json`, `addresses.json`, `contracts.json`, `networks.json`); markdown indexes (`docs/deployments.md`, `README.md` tables). Cite the file URL with the commit SHA; pin SHAs (`?ref=<sha>`) so the citation is content-addressed.

- **D5. Multi-chain enumeration.** If `protocol.chains.length > 1`, repeat D1–D4 per chain. Cross-chain deployments of the same logical contract get SEPARATE `admin_addresses[]` entries — one per chain. The chain field is part of the identity; do not collapse. If a chain has zero results, record `"D5: chain <name>: zero addresses surfaced from <sources tried>"` in unknowns[].

- **D6. Factory-discovered children.** For factory addresses surfaced in D1–D4, fetch the enumeration view via the read API (`/api/contract/read?...&method=allPools` / `getPool` / `getMarket` / `getVault`) and record each child with role like `"pool (from factory <0xFactory>)"`. **Cap at 50 children per factory.** Protocols with thousands of pools (Uniswap, Sushi) need dedicated ingestion — record the factory + the cap notice in unknowns[].

- **D7. Role taxonomy.** Every `admin_addresses[]` entry's `role` uses this controlled vocabulary (free-text suffixes OK for disambiguation, e.g. `"multisig (treasury)"`, but the leading token must match):

    `owner | admin | proxy_admin | governor | timelock | guardian | multisig | treasury | oracle | factory | router | token | pool | vault | other`

  Tentative classifications are encouraged. `actor_class` ∈ `eoa | multisig | timelock | governance | unknown` — use `unknown` when you found the address but didn't read its bytecode.

- **D8. Ratchet output integrity.** Every address in `admin_addresses[]` must trace to ≥1 fetched URL in evidence[]. Snippet-only sightings go in unknowns[] with a `D8` code, NOT in admin_addresses[].

### Discovery rationale framing

- `rationale.findings`: one entry per D-code, terse, factual. Per-address detail belongs in evidence[] and admin_addresses[], not here. Example: `"D1: 8 addresses surfaced from etherscan.io name-tag search for 'Aave V3'"`.
- `rationale.steelman`: ALWAYS null.
- `rationale.verdict`: one short line summarizing what corpora were walked and how many addresses were catalogued.
- `headline`: factual and quantitative — `"24 contracts catalogued across Ethereum, Arbitrum, and Base; 6 governance/admin and 18 protocol contracts."`.
- `short_headline`: under 60 chars — `"24 contracts across 3 chains"`.

### What discovery is NOT

- Not a verdict slice. `grade` must be `"unknown"`.
- Not exhaustive enumeration of leaf assets — record the factory + cap and move on (see D6).
- Not classification of trust assumptions — whether a multisig threshold is safe / timelock delay is sufficient / proxy admin is an EOA is the control slice's job.
- Not address-book reconciliation: when addressBook is non-empty, EXTEND it (find addresses prior runs missed) rather than re-cite the same addresses; re-cite only when you have new evidence for a refined role.

### protocol_metadata side-effects

While walking the corpora, populate every `protocol_metadata` field you can support with citations: `github`, `docs_url`, `audits` (one per D3 audit walked), `governance_forum`, `bug_bounty_url`, `security_contact`, `deployed_contracts_doc` (URL from D2), `upgradeability` (best-effort), and `about` (2–4 sentences sourced from docs/website, not memory). Discovery is the natural home for these — evaluation slices should not have to rediscover them.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "discovery",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Verifiability Unverified Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-us
- protocol.name:              Polymarket US
- protocol.chains:            (none recorded)
- protocol.category:          Prediction Market
- protocol.website:           https://polymarketexchange.com/
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               null

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
(no addresses pinned in this run — discover candidates from fetched website / GitHub / audit / explorer pages, record discovered addresses in evidence[] and protocol_metadata.admin_addresses, and put any reads you couldn't perform in unknowns[]. The next assessment will inherit your discoveries.)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: VERIFIABILITY

Evaluate whether an outsider can independently confirm what the deployed code does.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- V1. For each address you assess: is the bytecode verified on the chain's block explorer? Record the "Contract Source Code Verified" indicator. https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x... returns this as a top-level "verified" boolean plus "abiSource" ("etherscan" / "sourcify") and an inline ABI — useful when the explorer page is rate-limited. If the contract is a proxy, verify BOTH the proxy contract AND the current implementation contract. The same /api/contract/abi response auto-resolves proxies and includes a "proxy.implementation" address when present, so one call covers V1 + V6 in one shot. An explorer "Similar Match" on a well-known proxy pattern (Aragon AppProxyUpgradeable, ERC1967Proxy, OssifiableProxy, OZ TransparentUpgradeableProxy) is expected for that pattern and does NOT count as a verification gap on its own — what matters is that the implementation is independently verified.
- V2. Source-to-repo correspondence: for each verified contract, attempt to find a matching commit in the linked GitHub repos. Record evidence[].commit on a match. Independent compile/bytecode-match is NOT required for green — a recognized public repo whose structure and file contents correspond to the explorer-visible source is sufficient. If you did not pin a commit SHA or run a bytecode diff, record that plainly in unknowns[] and proceed; it is a scope limit, not a downgrade signal.
- V3. Audit coverage: for each URL in protocol.audit_links, open it and record: auditor name, audit date, the specific contracts / commit in scope. Flag audits that predate the current deployment by >6 months without a follow-up review.
- V4. Auditor recognition: the following firms are broadly recognized in Solidity: Trail of Bits, Zellic, Spearbit, OpenZeppelin, ConsenSys Diligence, Certora (formal verification), Quantstamp, Halborn, Peckshield, Sigma Prime, ChainSecurity, Ackee Blockchain, MixBytes, Statemind. Unknown firms are orange-at-best for any green-grade claim. Name the firm explicitly in evidence[].
- V5. Post-audit drift: compare the most recent in-scope audit(s) against the currently-deployed source, weighted by what each contract does and by what the changes actually contain. SCOPE — drift only downgrades the grade when ALL of the following hold: (i) the drifting contract is fund-custody / settlement / accounting-critical (NOT a peripheral router, lens, quoter, or pure-view contract that holds no balances); (ii) the changes are material — new functions, modified access control, modified accounting, modified fund flow — and not refactors / struct relocations / import reorgs / build or CI fixes / formatting; (iii) no later audit, fix-audit, or differential audit from a recognized firm covers the changed files (audits often pin a pre-fix commit while a follow-up reviews the delta — match by file scope, not by commit-hash equality). When you cite drift as a downgrade reason, name the specific behavior change (function added, role granted, accounting formula altered) — "N commits ahead" or "+X/-Y LOC" alone is not evidence of material drift. If you have not sampled the diff content (e.g. via the GitHub compare view or the top commits in the window), record drift as an unknowns[] entry rather than auto-downgrading; commit-count and LOC are starting signals, not findings.
- V6. Implementation vs proxy: a verified proxy with an unverified implementation is effectively unverified. State whether the implementation is verified separately.

EVIDENCE DISCIPLINE (read before writing findings[]):
- Do not assert a specific deploy-commit SHA, bytecode equivalence, or "identical to audited commit" unless you actually fetched the artifact that shows it (e.g., a deployed-addresses JSON you opened, an explorer page you read). Inferred or plausible matches belong in unknowns[], never in findings[] or evidence[].
- Evidence[] entries must correspond to pages/files you actually retrieved this run. A URL you did not open is not evidence.

Then write the steel-man section per Hard Rule 11.

Grade rules:
- green   = deployed bytecode verified on the explorer (proxy AND implementation if proxied; "Similar Match" on a standard proxy pattern is fine per V1), a public source repo exists whose contents correspond to the explorer-visible source, AND ≥1 audit from a recognized firm covering the currently-deployed contracts (≤6 months of drift OR drift was re-audited). A missing local compile-match is not a downgrade — record it in unknowns[] and still grade green if the other conditions hold.
- orange  = verified but with visible drift from the public repo, OR audit scope is stale relative to deployment, OR only minor / unknown-firm audits exist, OR only some of the main contracts are verified, OR proxy verified but implementation only partially verified.
- red     = unverified bytecode (or verified proxy with unverified implementation), OR no audit in protocol.audit_links, OR no public repo.
- unknown = reserved for when the protocol's verifiability posture genuinely cannot be assessed (e.g., explorer and repo both inaccessible for this protocol). Do NOT use unknown merely because you, the analyst, could not run a particular check such as a bytecode diff — that goes in unknowns[] while the grade is still assigned from the evidence you do have.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "verifiability",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Control Unverified Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-us
- protocol.name:              Polymarket US
- protocol.chains:            (none recorded)
- protocol.category:          Prediction Market
- protocol.website:           https://polymarketexchange.com/
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               null

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
(no addresses pinned in this run — discover candidates from fetched website / GitHub / audit / explorer pages, record discovered addresses in evidence[] and protocol_metadata.admin_addresses, and put any reads you couldn't perform in unknowns[]. The next assessment will inherit your discoveries.)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: CONTROL

Evaluate who can change the protocol's rules, how fast, and how broadly.

(Step 0 capability probe and the off-chain-only fallback live in the preamble — those rules apply here.)

### MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[])

- **C1.** For each address you assess: who is the contract owner / admin / pendingAdmin / governor — read these via the block explorer's "Read Contract" tab OR `https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=owner` (BARE method names: `&method=owner`, `&method=admin`, `&method=pendingOwner`, `&method=governor`). For Safes use `/api/safe/owners?chainId=<id>&address=0x...`. When a protocol has multiple major versions deployed (v2/v3/v4), perform C1 reads on the NEWEST deployment separately — newer deployments often have weaker control surfaces than the legacy core.
- **C2.** Upgrade mechanism: transparent proxy / UUPS / Beacon / Diamond / immutable. Identify the proxy admin address. Check upgradeability of GOVERNANCE contracts too — a Governor / Aragon Voting / OZ Governor is often itself a proxy whose admin is the Timelock. Asymmetry: when fund-holding cores are immutable AND governance has no admin path that reaches them, an upgradable Governor/Timelock is T3-only and must NOT drag the verdict below green on that basis alone (see grade rules and the "immutable cores" caveat). Only call upgradability "mixed" if you can name a concrete function on the upgradable surface that reaches T1 or T2 on user funds.
- **C3.** EXECUTION PATH (enumerate every stage, in order, with delays in seconds). The operative path is usually a chain (voting → scheduler → timelock → executor; or governor → queue → execute; or Aragon Voting → DualGovernance → EmergencyProtectedTimelock → AdminExecutor). For each stage, record (a) the contract address, (b) the delay constant name + value in seconds, (c) the URL you read it from (block-explorer Read Contract OR `/api/contract/read?...&method=MIN_DELAY&block=<n>`). Do NOT stop at the first timelock-shaped contract — if its admin is itself called by another contract, keep walking. The grading delay is the SUM OF DELAYS ON THE UNCONTESTED FAST PATH (shortest time a proposal with no opposition can go from submission to executable). Dynamic / contested extensions (veto signaling, rage quit, escrow delay) are modifiers, not the basis — note them separately.
- **C4.** Enumerate EVERY multisig with reachable control — main proxy admin, emergency activation, emergency execution, reseal / pause, gate-seal committees, tiebreaker, per-module admins. For each Safe, fetch threshold + owners + version via `/api/safe/owners?chainId=<id>&address=0x...` (response includes raw eth_call data, so the URL is citable evidence). Enumerate ops/council/incentives multisigs even when off the upgrade path — record their scope so a reader can see they are NOT on the upgrade path. For each: (a) address, (b) threshold / total signers, (c) signer identities classified as insider (team, paid auditors under ongoing engagement, mandated service providers) vs non-insider (independent community members, unaffiliated researchers), (d) the specific power held (upgrade, pause, parameter, etc.).
- **C5.** On-chain governance: Governor / GovernorBravo / OZ Governor / Aragon Voting with token-weighted voting? Record proposal threshold, voting period, quorum, and the timelock delay between queue and execute. Every numeric constant must come from a Read Contract call you can link to, or be in unknowns[] with the C-code. If votingDelay / votingPeriod are denominated in BLOCKS, convert to seconds at the chain's CURRENT block time (Ethereum mainnet ≈ 12s post-Merge, not the 15s in older Compound/Bravo deployments) — cite both block count and converted seconds.
- **C6.** EMERGENCY POWERS: separate emergency-pause / guardian role with a different time cap or different actor than the main upgrade authority? Record it explicitly.
- **C7.** POWER TIER (blast radius). For each privileged path in C3–C6, classify the WORST thing that path can do, choosing the highest applicable tier. Cite the specific function name and any on-chain bound — tier claims without a named function are unsupported.
    - **T1 — FUND-CRITICAL**: replace implementation of contracts holding user funds; change AMM math / accounting / collateral logic; mint unbacked debt or shares; pause withdrawals; drain user-fund treasury; change oracle to attacker-controlled source; replace upgrade admin with EOA.
    - **T2 — ECONOMICALLY MATERIAL**: change fee parameters within bounded ranges; redirect protocol fees; add/remove markets / collateral types; bounded inflation or token mint within hard-capped schedule; spend protocol-owned (non-user) treasury.
    - **T3 — GOVERNANCE-INTERNAL**: change voting rules, quorum, voting period, proposal threshold; upgrade the Governor itself; rotate Timelock admin; mint governance tokens within a capped annual schedule.
    - **T4 — OPERATIONAL**: incentives distribution, grants, ENS / frontend canonicalization, deployment coordination, periphery router deprecation.
  The grade is set by the HIGHEST tier reachable on the uncontested fast path, not the median. State the tier and the binding function in the verdict.

### Read Contract discipline (applies to C3, C4, C5)

Every numeric constant cited (timelock delays, voting periods, multisig thresholds, quorum percentages) must come from EITHER (a) a block-explorer Read Contract URL, OR (b) a DeFiPunkd `/api/contract/read` or `/api/safe/owners` URL (preferred with `&block=<n>` for content-addressed evidence), OR (c) an unknowns[] entry with the C-code. Docs / blog posts are corroboration only — they cannot be the sole citation for a value that is also readable on-chain.

### Off-chain-only substitute hierarchy (when grading_basis="off-chain-only" — see preamble Rule 16)

When on-chain reads were genuinely unreachable this run, eligible off-chain substitutes in priority order:
1. Linked audit PDFs (admin roles, multisig members, timelock delays usually enumerated).
2. Governance forum posts that quote constants from a successful on-chain proposal (cite post URL + linked execution-tx URL).
3. Official protocol docs pages with named addresses and roles (must be on a domain owned by the protocol).
4. GitHub README / SECURITY.md / governance/*.md at a pinned commit SHA.

Forbidden substitutes: third-party blog posts, X / Twitter threads, search-result snippets, model memory. Required degradation: any C-code citing a numeric constant from docs/forum/audit prose ONLY must also carry an `unknowns[]` entry with `-offchain` suffix noting "value not re-read on-chain in this run; corroboration only".

### Grade rules (apply the timelock bar conditional on the highest C7 tier reachable on the fast path)

Security Council standard (used below): a multisig qualifies as "Security Council" only if ALL of: ≥7 signers, ≥51% threshold, ≥50% non-insider signers, every signer publicly announced. Failing any criterion = NOT a Security Council, regardless of signer reputation.

- **green**: highest reachable tier is T3 or T4 regardless of timelock; OR T2 reachable with uncontested-fast-path delay ≥7 days; OR T1 reachable only via immutable contracts (T1 is unreachable); OR T1 reachable with uncontested-fast-path delay ≥7 days combined with a Security Council multisig; OR T1 reachable with uncontested-fast-path delay ≥7 days through active on-chain governance with broad token distribution.
- **orange**: T2 reachable with uncontested-fast-path delay >0 but <7 days; OR T1 reachable with uncontested-fast-path delay >0 but <7 days; OR a multisig failing one or more Security Council criteria sits on a T1/T2 path; OR unclear upgrade authority on a T1/T2 path; OR governance with very short timelock or low quorum on a T1/T2 path.
- **red**: T1 reachable with no timelock by a single EOA or 2-of-3 multisig; OR a T1 upgrade admin that is not a smart contract you can audit.
- **unknown**: completed the checklist but still cannot determine the upgrade authority OR cannot classify the highest tier reachable on the main contracts.

Tiering caveats:
- "Bounded" must be enforced ON-CHAIN to count as T2. A function that sets fees with no upper-bound check is T1 — cite the bound check.
- Recurring T2 economic extraction (e.g. fee redirect with no rate limit) approaches T1 over time. A single proposal that can permanently redirect all future revenue is T1.
- T3 assumes the governance contract cannot itself authorize a T1/T2 action without going through the same timelock. If governance can self-upgrade to bypass the timelock, T3 collapses into T1.
- Do not downgrade tier by hand-waving ("realistically governance would never…"). Tier on what the contract permits, not what feels likely.

Notes:
- **Dynamic / dual-governance timelocks** (Lido, Compound escrow veto): the rubric grades on the uncontested path because that is the path most upgrades take. A dynamic extension that fires only under stake-weighted opposition is a real protection — name it in the green steel-man, but it does not lift an orange fast path into green; state the tension in the verdict.
- **Immutable cores with upgradable governance** (Uniswap-style): if fund-holding contracts are immutable and have no admin-reachable function moving / freezing / re-routing user funds, the highest reachable tier on the upgrade path is T3 — green regardless of timelock. Don't grade this orange just because the Governor is a proxy — that's a C2 fact, not a downgrade. Downgrade only applies if you can cite a concrete function on the upgradable surface that reaches T1 or T2 (privileged hook, upgradable factory controlling fund-routing, fee-switch redirecting protocol revenue without bound).
- **The 7-day bar** reflects the exit-window standard — users need notice after a queued upgrade to withdraw if they disagree. The ability-to-exit slice grades the exit side; this slice grades the delay side; both must hold for users to actually benefit from the delay.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "control",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Ability to exit Unverified Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-us
- protocol.name:              Polymarket US
- protocol.chains:            (none recorded)
- protocol.category:          Prediction Market
- protocol.website:           https://polymarketexchange.com/
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               null

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
(no addresses pinned in this run — discover candidates from fetched website / GitHub / audit / explorer pages, record discovered addresses in evidence[] and protocol_metadata.admin_addresses, and put any reads you couldn't perform in unknowns[]. The next assessment will inherit your discoveries.)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: ABILITY-TO-EXIT

Evaluate whether users can withdraw their funds on their own terms, even under adversarial admin conditions.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- E1. Enumerate every user-facing exit function in the main contracts: withdraw, redeem, burn, requestWithdrawal, claim, exit, etc. List them by name. Do NOT treat the contract as a monolith.
- E2. For EACH exit function in E1: identify its access modifiers and any pause guards (e.g. _checkResumed, whenNotPaused, onlyRole). Functions that gate REQUEST PLACEMENT often differ from functions that CLAIM FINALIZED FUNDS — check both separately.
- E3. For each pause guard: identify the role holder (which address holds PAUSE_ROLE / GUARDIAN / etc.) and the maximum pause duration. Specifically check whether PAUSE_INFINITELY (or equivalent uncapped pause) is callable, and which actor can call it (single multisig vs governance vote). For role-holder reads use https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=hasRole&args=0x...,0x... or &method=getRoleAdmin&args=0x.... For "is currently paused" checks use &method=paused or &method=isPaused&args=<resume-code>. Use the BARE method name (no parens). Cite the URL with &block=<n> in evidence[].
- E4. EMERGENCY vs GOVERNANCE pause distinction: many protocols have a fast-acting emergency pause capped at N days and a slow governance pause that can be indefinite. Record both paths separately if present, with their time caps and actor classes.
- E5. Queued redemption: documented maximum queue duration, daily withdrawal caps, whether the queue itself is pausable.
- E6. Forced-exit / escape-hatch / permissionless emergency-exit mechanism for adversarial-admin scenarios.
- E7. Frontend dependency: confirm exit functions are directly callable on-chain (e.g. via Etherscan write tab or a generic wallet) without the project's frontend.

Then write the steel-man section per Hard Rule 11. Common red-vs-orange tension on this slice: indefinite pause exists (suggests red) BUT the realistic emergency path is time-capped AND claims of already-finalized exits are not pause-gated (suggests orange). Resolve this by stating who can do what for how long, not by stopping at the worst-case sentence.

Grade rules:
- green   = permissionless exit; pause is either absent, narrowly scoped to clearly-described emergencies with auto-expiry, or capped at ≤7 days; no frontend dependency for exit; claims of already-finalized exits are not pause-gated under any path.
- orange  = pausable with broad scope OR indefinite pause is reachable only through governance vote (not unilateral admin action), OR queued redemption with documented max > 7 days, OR claims-of-finalized are exempt but new-request placement can be paused indefinitely by governance.
- red     = exit requires admin signature, OR ANY actor (including governance) can pause CLAIMS of finalized exits indefinitely, OR there is no on-chain exit function at all (purely custodial), OR pause is held by a single EOA / 2-of-3 multisig with no time cap.
- unknown = checklist incomplete after checking the sources above.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "ability-to-exit",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Autonomy Unverified Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-us
- protocol.name:              Polymarket US
- protocol.chains:            (none recorded)
- protocol.category:          Prediction Market
- protocol.website:           https://polymarketexchange.com/
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               null

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
(no addresses pinned in this run — discover candidates from fetched website / GitHub / audit / explorer pages, record discovered addresses in evidence[] and protocol_metadata.admin_addresses, and put any reads you couldn't perform in unknowns[]. The next assessment will inherit your discoveries.)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: AUTONOMY

Evaluate this protocol's autonomy: can a failure of anything outside its own contracts cause theft or loss of user principal, loss of unclaimed yield, or materially change the protocol's expected performance? "Autonomy" is not "has zero external touchpoints" — it is "external failures are either survivable or recoverable without user loss". This slice adapts DefiScan v1's Autonomy dimension; dependencies are one of several criteria, not the whole frame.

GUARDRAILS (read before grading):
- Category alone (Liquid Staking, Bridge, RWA Lending, Restaking, …) does NOT force a grade. A category is a hint about where to look; the grade must come from the concrete A1–A9 findings below.
- Base-chain consensus (Ethereum PoS, the chain's validator set, the canonical Deposit Contract at 0x00000000219ab540356cBB839Cbe05303d7705Fa) is the SUBSTRATE, not a dependency, for any protocol deployed on that chain. Do not list "depends on Ethereum" as a finding.
- Oracles or other integrations used by DOWNSTREAM protocols that happen to read this protocol's token (e.g. Chainlink stETH/USD consumed by Aave) are NOT this protocol's dependencies. Count only what THIS protocol's contracts call or trust on-chain. If a feed or contract appears in the protocol's docs only as reference material for third-party integrators, EXCLUDE IT ENTIRELY — do not log it as a finding even with a "peripheral" or "referenced only" caveat.
- "Upgradeable admin can change things" belongs to the CONTROL slice; only count it here when the upgrade surface lets governance silently swap an external dependency (see A9).
- Underlying-asset risk in opt-in, isolated markets is NOT autonomy-red on its own. When a protocol wraps third-party yield-bearing assets (LSTs, LRTs, ERC-4626 vaults, lending receipts, restaked tokens) into per-market silos that users explicitly choose, a failure of one underlying does NOT propagate to other markets and is risk the user opted into per-market. Record it under A4 with depth and propagation scope, but do not let it alone drive a red verdict — red requires an external dependency that cross-cuts the protocol or that the user did not opt into at deposit time. A failure mode that is "if the LRT you deposited is hacked, your principal in that LRT-backed market is impaired" is the underlying's autonomy story, not this protocol's; grade it on whether THIS protocol introduces additional dependencies on top.
- Sub-module enumeration is mandatory before grading. If the protocol ships distinct product lines or modules (e.g., a v2 core AMM plus a newer perps/funding-rate module, a lending pool plus a separate vault layer, an L1 core plus a cross-chain extension), enumerate each in findings and grade against the WORST module weighted by its share of TVS or its blast radius. A green core does not rescue an orange/red sub-module; conversely, a small red sub-module with capped TVS may bound the overall grade to orange. Name each module by its on-chain factory or router address. If you do not know whether a module exists, that is an unknowns[] entry, not silence. EXPLICIT TVS WEIGHTING: in the verdict, state each module's approximate share of total protocol TVS (use "~X%" if exact figures unavailable; check DeFiLlama or block-explorer balances on the module's main contract) and how that share informs the weighted grade. Format: "Module A holds ~X% of TVS (grade: <g>); Module B holds ~Y% (grade: <g>); weighted overall = <grade> because <reason>." If a red sub-module holds <5% of total TVS and is capped, the overall grade may be orange; if it holds >25%, the overall grade is red. Do not let qualitative reasoning substitute for the percentages — write the numbers.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- A1. External contract calls. Enumerate every external contract the core contracts call or read from (oracles, price feeds, AMM pools, lending pools, staking/deposit contracts, yield wrappers). For each, identify the address, the provider, and what user-facing function of this protocol would break or mis-price if that external contract paused, mis-reported, or behaved adversarially. Grep for "oracle", "aggregator", "getPrice", "latestAnswer", "chainlink", "pyth", "redstone" as a starting point. To verify an oracle is live and what it currently reports, hit https://defipunkd.com/api/contract/read?chainId=<id>&address=<oracle>&method=latestAnswer (or &method=latestRoundData, &method=getPrice, &method=description; use the BARE method name without parens) and cite the URL — the response includes blockNumber/blockHash and rawReturnData, which is stronger evidence than a docs page about which feed "should" be used.
- A2. Off-chain actor committees reporting INTO the protocol. Oracle committees, guardian multisigs, DAO-selected validator sets acting as protocol reporters, exit-bus signers, fraud-proof challengers. For each, record committee size, quorum, who picks the members, and what mis-reporting could do (mint, burn, finalize withdrawal, freeze). Distinguish this from governance admins (control slice). NOTE ON STAKING PROTOCOLS: validator slashing and node-operator misbehavior are properties of the base-chain substrate, NOT external dependencies, when the operator set is diversified enough that a coordinated failure caps at <5% principal loss. Count validator/operator risk under A2 ONLY if the operator set is small, non-diversified, or lacks bonding / slashing-insurance / diversification mitigations. A curated set of 30+ independent operators with documented diversification falls under the mitigated path; a 3-operator LST does not. Do not cite the protocol's own risk disclosure as evidence that operator failure = principal loss unless you also check the diversification and bond mitigations.
- A3. Bridge / cross-chain messaging dependencies. Only count bridges that carry material TVL or are required for a core user flow. For each, name the bridge operator (canonical L1↔L2, LayerZero, Wormhole, Axelar, custom multisig), the trust model (canonical, optimistic, light-client, guardian set), and what fraction of TVL or users ride on it. "wstETH exists on 15 chains" is not a finding unless material TVL sits there. Before listing any non-primary chain deployment as a dependency, verify it is still operational as of analysis_date — retired or sunset deployments (e.g., Lido-on-Terra, Lido-on-Solana) belong in unknowns[] or should be omitted, never cited as a current dependency.
- A4. Nested collateral / restaking chains. For restaking / LRT / receipt-of-receipt designs: record the depth of the collateral chain, every actor with slashing or freezing power at each level, and whether a failure N levels deep propagates to user principal here.
- A5. Fork lineage (silent check). If DeFiLlama's forkedFrom is non-empty, record it as one finding and move on. If empty, do NOT add a placeholder finding; it adds noise.
- A6. Fallback mechanisms and circuit breakers. What catches an external failure? Sanity-check contracts on oracle reports, rebase bounds, pause paths triggered by bad prices, second-opinion oracles, max-per-block throughput caps, withdrawal queues that absorb bad reports. Record which A1–A4 risks are mitigated by which fallback, and which are unmitigated. For EACH fallback you cite, state its activation status explicitly: (i) LIVE and enforcing on-chain today, (ii) DEPLOYED but not yet wired / activated (e.g., interface exists but the address is zero or the role is unassigned), or (iii) DOCUMENTED / PROPOSED only (forum post, LIP draft, audit pending). Only (i) counts as mitigation for the grade. A fallback in state (ii) or (iii) should be noted but must not reduce the risk in your steel-man or verdict. If you cannot determine activation status, add an unknowns[] entry rather than assume it is live.
- A7. Sequencer / L1-liveness dependency BEYOND the base-chain substrate. SCOPE — sequencer risk only counts here when the protocol IS its own L2/L3 appchain or app-rollup, where the sequencer is part of the protocol's own stack and a freeze is a protocol-level outage. A protocol permissionlessly deployed on a third-party L2 inherits that L2's sequencer as substrate, not an A7 dependency. Record the sequencer/DA trust model when A7 applies.
- A8. Keeper / relayer / off-chain bot liveness. Protocols that need permissionless-but-necessary off-chain actors (liquidation bots, auto-compounders, deposit relayers, intent solvers). Record whether the role is permissionless, what degrades if nobody runs it (yield paused, bad debt accumulates, positions go stale), and whether the failure mode is graceful or catastrophic.
- A9. Governance-mutable dependency surface. Can an admin or DAO action silently INTRODUCE a NEW EXTERNAL dependency — swap the oracle address to a different provider, register a new staking module that calls an untrusted contract, add a new bridge, route SY through a new external vault — without an exit window for users? Check the upgrade / router / module-registry contracts. Answer: which EXTERNAL dependencies are governance-mutable, who holds that power, and whether there is a timelock or exit window. SCOPE LIMIT — read carefully: A9 is about the *external dependency surface*, not the upgrade surface in general. "The proxyAdmin / EOA can upgrade the router implementation to arbitrary bytecode" is a CONTROL-slice finding (admin can rug), NOT an autonomy-A9 finding. A9 fires only when the upgrade specifically swaps out or adds a contract that THIS protocol calls or trusts (e.g., changing the oracle address from Chainlink to a malicious feed, registering a new SY adapter that points to a third-party vault, redirecting a bridge endpoint). If the only finding is "admin can change implementation," do not log it under A9 and do not let it drive the autonomy grade — note it under control instead. The autonomy-relevant version of the same upgrade key is "admin can swap [specific external address X] without timelock"; that requires identifying the specific external dependency that becomes mutable.

STEEL-MAN (per Hard Rule 13): write one-sentence strongest arguments for red, orange, and green using the A1–A9 findings.

IMPACTED TVS ESTIMATE: the headline MUST include a rough impacted-TVS figure — the fraction of protocol TVS that could be lost or frozen if the worst-unmitigated dependency you identified failed. Use "~X%" if exact numbers are unavailable, "<1%" for de minimis, "unclear" only if A1–A9 left the question genuinely open (in which case grade=unknown is usually correct). Do NOT substitute qualitative phrases like "significant" — give a number or bracket.

GRADE ANCHORS (mapped to DefiScan v1 stages):
- green = Stage 2 equivalent. Failure of any external dependency cannot cause loss of user principal or unclaimed yield. Either there are no material external dependencies, or every critical one has a documented fallback (A6) that keeps users whole. Governance cannot silently introduce new dependencies without an exit window (A9). Impacted TVS under any single-dependency failure: effectively 0.
- orange = Stage 1 equivalent. Failure of some external dependency can cause loss of unclaimed yield, or can materially change expected performance (pause withdrawals, freeze positions, degrade price quality), but cannot cause loss of principal. Committee-based oracles with sanity checks, canonical-only bridges, fallback paths that exist but are incomplete, or governance-mutable dependencies protected by a ≥7-day timelock. Impacted TVS is bounded and recoverable.
- red = Stage 0 equivalent. Failure of an external dependency CAN cause theft or loss of principal. Examples: single-provider oracle with no sanity check or fallback, material TVL on a non-canonical bridge with a guardian multisig, governance can hot-swap oracles or add staking modules with no timelock or exit window, unmitigated keeper-liveness dependency where positions become insolvent if bots stop. Impacted TVS is material.
- unknown = checklist incomplete after inspecting source + verified contracts. Prefer unknown over guessing when A1/A6 could not be reconstructed. RESERVE unknown for cases where the CORE ARCHITECTURE itself is unverifiable — not for cases where you merely cannot enumerate every per-market dependency in a multi-market protocol. If the core router/factory/oracle architecture is verifiable on-chain and you can determine whether the core requires external dependencies, grade the architecture even when an exhaustive per-market external-dependency census is infeasible. Acknowledge the per-market gap in unknowns[] but still issue a grade. Refusing to grade a multi-market protocol because you cannot list every SY/vault/market is over-use of unknown; grade the architecture and say so.

PROMPT-META CHECK (per Hard Rule 17): before finalizing, verify the verdict cites concrete contract addresses, docs, or code — not the rubric itself. If your verdict says "the protocol belongs to a category the rubric marks red", rewrite it with the A1–A9 finding that actually justifies the grade, or drop to grade=unknown.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "autonomy",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Open Access Unverified Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-us
- protocol.name:              Polymarket US
- protocol.chains:            (none recorded)
- protocol.category:          Prediction Market
- protocol.website:           https://polymarketexchange.com/
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               null

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
(no addresses pinned in this run — discover candidates from fetched website / GitHub / audit / explorer pages, record discovered addresses in evidence[] and protocol_metadata.admin_addresses, and put any reads you couldn't perform in unknowns[]. The next assessment will inherit your discoveries.)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: OPEN-ACCESS

Evaluate who is allowed to use the protocol and whether any of that permission is granted off-chain.

Scope: this slice is about ADMISSION — who can enter, exit, or transact. Operator LIVENESS (what breaks if keepers/oracles go offline) is assessed in the dependencies slice and is out of scope for the grade here. You may note operator dependencies as context, but do not let "the protocol halts if operator X disappears" drive the access grade on its own; that belongs in dependencies. Source verification / contract verification on block explorers is assessed in the verifiability slice and is out of scope here — do NOT let "contract is unverified" drive the access grade.

Framing: the smart contracts are the access layer; frontends are UX. A permissionless contract is reachable by any client (SDK, third-party UI, aggregator, wallet integration). Frontend ToS, IP geo-blocking, and wallet screening are publisher policies on one specific client — they are reported as context but do NOT determine the grade. The grade hinges on (1) what the contract itself permits, and (2) whether the protocol is practically reachable without the official publisher's cooperation.

Meta-check before finalizing: if your verdict cites phrases from this prompt as evidence ("the protocol meets the 'credible alternatives' condition", "this fits the 'documented fallback' rule"), redo the verdict. The prompt describes the rubric; evidence must come from the protocol. A verdict should cite what the protocol does, not what the rubric says.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- A1. Whitelist / allowlist modifiers in user-facing entry points. Grep for "onlyWhitelisted", "onlyRole", "allowlist", "isAccredited", "isKYCed". Note which functions are gated and who can add/remove from the list.
- A2. Off-chain operators in the admission path: keepers, sequencers, privileged relayers, oracle posters whose approval is required to admit a user action (not just to keep the protocol live). For each, identify whether the role is held by a single operator, a permissioned committee, or is permissionless. Enumerate per user-facing function class (deposit vs withdraw-request vs claim-finalized vs transfer) which ones require operator approval to be admitted, and which ones admit users unconditionally. A function whose placement is unconditional but whose downstream settlement depends on an operator is an admission-permissionless function — flag the liveness dependency as context and defer its grading weight to the dependencies slice.
- A3. Frontend restrictions on the official interface — record as context, not as a grade lever. Distinguish:
    - A3-passive: boilerplate ToS clauses (sanctions attestation, restricted-territory self-certification, VPN-circumvention prohibition, "comply with applicable law" eligibility, age of majority).
    - A3-active: runtime enforcement — IP-based geo-blocking, wallet-address screening against a sanctions oracle (Chainalysis, TRM, Elliptic), KYC wall, rendering-blocking jurisdiction banner.
  Record findings under the correct tier. Quote ToS text or banner text in evidence[].shows. These findings populate the headline and rationale but do NOT move the grade by themselves; the grade is set by A1, A2, and the A3b path check below.
- A3b. Independent access paths (the operative grade input). Enumerate paths that do not require the official publisher's cooperation:
    - Published SDK / library / CLI for direct contract interaction.
    - Third-party frontends operated by separate legal entities.
    - Wallet-integrated access (MetaMask Swaps, Safe apps, etc.).
    - DEX / lending / yield aggregators that route through the contracts.
  Record at least one concrete link per path that exists. The protocol does NOT have to self-document these — the test is existence, not UX cost. An A3b-i redistribution of the official UI bound by the same ToS does NOT count as an independent path.
- A4. Sanctions / compliance tooling at the contract level: does the protocol check addresses against OFAC lists or similar on-chain blocklists in the contract itself? (Frontend-only screening belongs in A3.)
- A5. Differentiate read access vs write access: many protocols are read-permissionless (anyone can view state) but write-gated (only certain addresses can deposit/borrow). Record both.
- A6. ToS / Legal links: locate them on the website and produce a VERBATIM quote of any jurisdictional, sanctions, or eligibility clause in evidence[].shows. If you cannot extract the clause text verbatim (SPA render failure, paywall, dead link, etc.), do NOT paraphrase or infer from general knowledge — record the ToS URL in unknowns[] with the reason extraction failed. Assertions about ToS content without a verbatim quote will be downweighted by reviewers.

Then write the steel-man section per Hard Rule 11.

Grade rules (admission-focused; liveness concerns belong in dependencies; source verification belongs in verifiability):
- green   = no contract-level whitelist/KYC on user entry/exit; no operator approval required to admit a user action; AND at least one independent A3b path exists (published SDK, third-party frontend, wallet integration, or aggregator routing). Frontend ToS posture and A3-active enforcement on the official UI do NOT block green when contracts are permissionless and an independent path exists — they are reported as context.
- orange  = contracts admit users unconditionally, BUT the protocol is operationally captured by the official publisher: no published SDK, no third-party frontend, no wallet integration, no aggregator routing. The contract is theoretically open but practically reachable only through the official UI. Also applies when admission requires approval from a permissioned committee that is governance-managed with a documented replacement procedure.
- red     = contract-level whitelist / KYC on user entry/exit, OR admission of a core user action requires approval from a single privileged operator or a small committee with no documented replacement procedure, OR enforces an on-chain blocklist updatable by a single party.
- unknown = checklist incomplete after checking the sources above.

Default-grade guidance: when contracts are fully permissionless AND any A3b independent path exists, the default grade is green regardless of frontend ToS or A3-active enforcement on the official UI. Frontend geo-blocking, sanctions-oracle wallet screening, and ToS sanctions clauses are publisher policies on one client and are reported in findings/headline as context, not as grade levers. To grade orange on operational-capture grounds, the auditor must affirmatively show that ALL independent paths are absent or also gated.

Guideline on committees: where admission depends on a multi-operator committee, the relevant axes are (a) set size, (b) whether replacement/rotation is governed on-chain, (c) whether the replacement procedure is publicly documented. A large set with on-chain governance replacement should not be graded as a single-party operator even if rotation is not instantaneous. A small set with informal replacement should be treated as a single-party operator.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "open-access",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Audit all 5 dimensions · one prompt Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-us
- protocol.name:              Polymarket US
- protocol.chains:            (none recorded)
- protocol.category:          Prediction Market
- protocol.website:           https://polymarketexchange.com/
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               null

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
(no addresses pinned in this run — discover candidates from fetched website / GitHub / audit / explorer pages, record discovered addresses in evidence[] and protocol_metadata.admin_addresses, and put any reads you couldn't perform in unknowns[]. The next assessment will inherit your discoveries.)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: CONTROL

Evaluate who can change the protocol's rules, how fast, and how broadly.

(Step 0 capability probe and the off-chain-only fallback live in the preamble — those rules apply here.)

### MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[])

- **C1.** For each address you assess: who is the contract owner / admin / pendingAdmin / governor — read these via the block explorer's "Read Contract" tab OR `https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=owner` (BARE method names: `&method=owner`, `&method=admin`, `&method=pendingOwner`, `&method=governor`). For Safes use `/api/safe/owners?chainId=<id>&address=0x...`. When a protocol has multiple major versions deployed (v2/v3/v4), perform C1 reads on the NEWEST deployment separately — newer deployments often have weaker control surfaces than the legacy core.
- **C2.** Upgrade mechanism: transparent proxy / UUPS / Beacon / Diamond / immutable. Identify the proxy admin address. Check upgradeability of GOVERNANCE contracts too — a Governor / Aragon Voting / OZ Governor is often itself a proxy whose admin is the Timelock. Asymmetry: when fund-holding cores are immutable AND governance has no admin path that reaches them, an upgradable Governor/Timelock is T3-only and must NOT drag the verdict below green on that basis alone (see grade rules and the "immutable cores" caveat). Only call upgradability "mixed" if you can name a concrete function on the upgradable surface that reaches T1 or T2 on user funds.
- **C3.** EXECUTION PATH (enumerate every stage, in order, with delays in seconds). The operative path is usually a chain (voting → scheduler → timelock → executor; or governor → queue → execute; or Aragon Voting → DualGovernance → EmergencyProtectedTimelock → AdminExecutor). For each stage, record (a) the contract address, (b) the delay constant name + value in seconds, (c) the URL you read it from (block-explorer Read Contract OR `/api/contract/read?...&method=MIN_DELAY&block=<n>`). Do NOT stop at the first timelock-shaped contract — if its admin is itself called by another contract, keep walking. The grading delay is the SUM OF DELAYS ON THE UNCONTESTED FAST PATH (shortest time a proposal with no opposition can go from submission to executable). Dynamic / contested extensions (veto signaling, rage quit, escrow delay) are modifiers, not the basis — note them separately.
- **C4.** Enumerate EVERY multisig with reachable control — main proxy admin, emergency activation, emergency execution, reseal / pause, gate-seal committees, tiebreaker, per-module admins. For each Safe, fetch threshold + owners + version via `/api/safe/owners?chainId=<id>&address=0x...` (response includes raw eth_call data, so the URL is citable evidence). Enumerate ops/council/incentives multisigs even when off the upgrade path — record their scope so a reader can see they are NOT on the upgrade path. For each: (a) address, (b) threshold / total signers, (c) signer identities classified as insider (team, paid auditors under ongoing engagement, mandated service providers) vs non-insider (independent community members, unaffiliated researchers), (d) the specific power held (upgrade, pause, parameter, etc.).
- **C5.** On-chain governance: Governor / GovernorBravo / OZ Governor / Aragon Voting with token-weighted voting? Record proposal threshold, voting period, quorum, and the timelock delay between queue and execute. Every numeric constant must come from a Read Contract call you can link to, or be in unknowns[] with the C-code. If votingDelay / votingPeriod are denominated in BLOCKS, convert to seconds at the chain's CURRENT block time (Ethereum mainnet ≈ 12s post-Merge, not the 15s in older Compound/Bravo deployments) — cite both block count and converted seconds.
- **C6.** EMERGENCY POWERS: separate emergency-pause / guardian role with a different time cap or different actor than the main upgrade authority? Record it explicitly.
- **C7.** POWER TIER (blast radius). For each privileged path in C3–C6, classify the WORST thing that path can do, choosing the highest applicable tier. Cite the specific function name and any on-chain bound — tier claims without a named function are unsupported.
    - **T1 — FUND-CRITICAL**: replace implementation of contracts holding user funds; change AMM math / accounting / collateral logic; mint unbacked debt or shares; pause withdrawals; drain user-fund treasury; change oracle to attacker-controlled source; replace upgrade admin with EOA.
    - **T2 — ECONOMICALLY MATERIAL**: change fee parameters within bounded ranges; redirect protocol fees; add/remove markets / collateral types; bounded inflation or token mint within hard-capped schedule; spend protocol-owned (non-user) treasury.
    - **T3 — GOVERNANCE-INTERNAL**: change voting rules, quorum, voting period, proposal threshold; upgrade the Governor itself; rotate Timelock admin; mint governance tokens within a capped annual schedule.
    - **T4 — OPERATIONAL**: incentives distribution, grants, ENS / frontend canonicalization, deployment coordination, periphery router deprecation.
  The grade is set by the HIGHEST tier reachable on the uncontested fast path, not the median. State the tier and the binding function in the verdict.

### Read Contract discipline (applies to C3, C4, C5)

Every numeric constant cited (timelock delays, voting periods, multisig thresholds, quorum percentages) must come from EITHER (a) a block-explorer Read Contract URL, OR (b) a DeFiPunkd `/api/contract/read` or `/api/safe/owners` URL (preferred with `&block=<n>` for content-addressed evidence), OR (c) an unknowns[] entry with the C-code. Docs / blog posts are corroboration only — they cannot be the sole citation for a value that is also readable on-chain.

### Off-chain-only substitute hierarchy (when grading_basis="off-chain-only" — see preamble Rule 16)

When on-chain reads were genuinely unreachable this run, eligible off-chain substitutes in priority order:
1. Linked audit PDFs (admin roles, multisig members, timelock delays usually enumerated).
2. Governance forum posts that quote constants from a successful on-chain proposal (cite post URL + linked execution-tx URL).
3. Official protocol docs pages with named addresses and roles (must be on a domain owned by the protocol).
4. GitHub README / SECURITY.md / governance/*.md at a pinned commit SHA.

Forbidden substitutes: third-party blog posts, X / Twitter threads, search-result snippets, model memory. Required degradation: any C-code citing a numeric constant from docs/forum/audit prose ONLY must also carry an `unknowns[]` entry with `-offchain` suffix noting "value not re-read on-chain in this run; corroboration only".

### Grade rules (apply the timelock bar conditional on the highest C7 tier reachable on the fast path)

Security Council standard (used below): a multisig qualifies as "Security Council" only if ALL of: ≥7 signers, ≥51% threshold, ≥50% non-insider signers, every signer publicly announced. Failing any criterion = NOT a Security Council, regardless of signer reputation.

- **green**: highest reachable tier is T3 or T4 regardless of timelock; OR T2 reachable with uncontested-fast-path delay ≥7 days; OR T1 reachable only via immutable contracts (T1 is unreachable); OR T1 reachable with uncontested-fast-path delay ≥7 days combined with a Security Council multisig; OR T1 reachable with uncontested-fast-path delay ≥7 days through active on-chain governance with broad token distribution.
- **orange**: T2 reachable with uncontested-fast-path delay >0 but <7 days; OR T1 reachable with uncontested-fast-path delay >0 but <7 days; OR a multisig failing one or more Security Council criteria sits on a T1/T2 path; OR unclear upgrade authority on a T1/T2 path; OR governance with very short timelock or low quorum on a T1/T2 path.
- **red**: T1 reachable with no timelock by a single EOA or 2-of-3 multisig; OR a T1 upgrade admin that is not a smart contract you can audit.
- **unknown**: completed the checklist but still cannot determine the upgrade authority OR cannot classify the highest tier reachable on the main contracts.

Tiering caveats:
- "Bounded" must be enforced ON-CHAIN to count as T2. A function that sets fees with no upper-bound check is T1 — cite the bound check.
- Recurring T2 economic extraction (e.g. fee redirect with no rate limit) approaches T1 over time. A single proposal that can permanently redirect all future revenue is T1.
- T3 assumes the governance contract cannot itself authorize a T1/T2 action without going through the same timelock. If governance can self-upgrade to bypass the timelock, T3 collapses into T1.
- Do not downgrade tier by hand-waving ("realistically governance would never…"). Tier on what the contract permits, not what feels likely.

Notes:
- **Dynamic / dual-governance timelocks** (Lido, Compound escrow veto): the rubric grades on the uncontested path because that is the path most upgrades take. A dynamic extension that fires only under stake-weighted opposition is a real protection — name it in the green steel-man, but it does not lift an orange fast path into green; state the tension in the verdict.
- **Immutable cores with upgradable governance** (Uniswap-style): if fund-holding contracts are immutable and have no admin-reachable function moving / freezing / re-routing user funds, the highest reachable tier on the upgrade path is T3 — green regardless of timelock. Don't grade this orange just because the Governor is a proxy — that's a C2 fact, not a downgrade. Downgrade only applies if you can cite a concrete function on the upgradable surface that reaches T1 or T2 (privileged hook, upgradable factory controlling fund-routing, fee-switch redirecting protocol revenue without bound).
- **The 7-day bar** reflects the exit-window standard — users need notice after a queued upgrade to withdraw if they disagree. The ability-to-exit slice grades the exit side; this slice grades the delay side; both must hold for users to actually benefit from the delay.

---

### Slice: ABILITY-TO-EXIT

Evaluate whether users can withdraw their funds on their own terms, even under adversarial admin conditions.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- E1. Enumerate every user-facing exit function in the main contracts: withdraw, redeem, burn, requestWithdrawal, claim, exit, etc. List them by name. Do NOT treat the contract as a monolith.
- E2. For EACH exit function in E1: identify its access modifiers and any pause guards (e.g. _checkResumed, whenNotPaused, onlyRole). Functions that gate REQUEST PLACEMENT often differ from functions that CLAIM FINALIZED FUNDS — check both separately.
- E3. For each pause guard: identify the role holder (which address holds PAUSE_ROLE / GUARDIAN / etc.) and the maximum pause duration. Specifically check whether PAUSE_INFINITELY (or equivalent uncapped pause) is callable, and which actor can call it (single multisig vs governance vote). For role-holder reads use https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=hasRole&args=0x...,0x... or &method=getRoleAdmin&args=0x.... For "is currently paused" checks use &method=paused or &method=isPaused&args=<resume-code>. Use the BARE method name (no parens). Cite the URL with &block=<n> in evidence[].
- E4. EMERGENCY vs GOVERNANCE pause distinction: many protocols have a fast-acting emergency pause capped at N days and a slow governance pause that can be indefinite. Record both paths separately if present, with their time caps and actor classes.
- E5. Queued redemption: documented maximum queue duration, daily withdrawal caps, whether the queue itself is pausable.
- E6. Forced-exit / escape-hatch / permissionless emergency-exit mechanism for adversarial-admin scenarios.
- E7. Frontend dependency: confirm exit functions are directly callable on-chain (e.g. via Etherscan write tab or a generic wallet) without the project's frontend.

Then write the steel-man section per Hard Rule 11. Common red-vs-orange tension on this slice: indefinite pause exists (suggests red) BUT the realistic emergency path is time-capped AND claims of already-finalized exits are not pause-gated (suggests orange). Resolve this by stating who can do what for how long, not by stopping at the worst-case sentence.

Grade rules:
- green   = permissionless exit; pause is either absent, narrowly scoped to clearly-described emergencies with auto-expiry, or capped at ≤7 days; no frontend dependency for exit; claims of already-finalized exits are not pause-gated under any path.
- orange  = pausable with broad scope OR indefinite pause is reachable only through governance vote (not unilateral admin action), OR queued redemption with documented max > 7 days, OR claims-of-finalized are exempt but new-request placement can be paused indefinitely by governance.
- red     = exit requires admin signature, OR ANY actor (including governance) can pause CLAIMS of finalized exits indefinitely, OR there is no on-chain exit function at all (purely custodial), OR pause is held by a single EOA / 2-of-3 multisig with no time cap.
- unknown = checklist incomplete after checking the sources above.

---

### Slice: AUTONOMY

Evaluate this protocol's autonomy: can a failure of anything outside its own contracts cause theft or loss of user principal, loss of unclaimed yield, or materially change the protocol's expected performance? "Autonomy" is not "has zero external touchpoints" — it is "external failures are either survivable or recoverable without user loss". This slice adapts DefiScan v1's Autonomy dimension; dependencies are one of several criteria, not the whole frame.

GUARDRAILS (read before grading):
- Category alone (Liquid Staking, Bridge, RWA Lending, Restaking, …) does NOT force a grade. A category is a hint about where to look; the grade must come from the concrete A1–A9 findings below.
- Base-chain consensus (Ethereum PoS, the chain's validator set, the canonical Deposit Contract at 0x00000000219ab540356cBB839Cbe05303d7705Fa) is the SUBSTRATE, not a dependency, for any protocol deployed on that chain. Do not list "depends on Ethereum" as a finding.
- Oracles or other integrations used by DOWNSTREAM protocols that happen to read this protocol's token (e.g. Chainlink stETH/USD consumed by Aave) are NOT this protocol's dependencies. Count only what THIS protocol's contracts call or trust on-chain. If a feed or contract appears in the protocol's docs only as reference material for third-party integrators, EXCLUDE IT ENTIRELY — do not log it as a finding even with a "peripheral" or "referenced only" caveat.
- "Upgradeable admin can change things" belongs to the CONTROL slice; only count it here when the upgrade surface lets governance silently swap an external dependency (see A9).
- Underlying-asset risk in opt-in, isolated markets is NOT autonomy-red on its own. When a protocol wraps third-party yield-bearing assets (LSTs, LRTs, ERC-4626 vaults, lending receipts, restaked tokens) into per-market silos that users explicitly choose, a failure of one underlying does NOT propagate to other markets and is risk the user opted into per-market. Record it under A4 with depth and propagation scope, but do not let it alone drive a red verdict — red requires an external dependency that cross-cuts the protocol or that the user did not opt into at deposit time. A failure mode that is "if the LRT you deposited is hacked, your principal in that LRT-backed market is impaired" is the underlying's autonomy story, not this protocol's; grade it on whether THIS protocol introduces additional dependencies on top.
- Sub-module enumeration is mandatory before grading. If the protocol ships distinct product lines or modules (e.g., a v2 core AMM plus a newer perps/funding-rate module, a lending pool plus a separate vault layer, an L1 core plus a cross-chain extension), enumerate each in findings and grade against the WORST module weighted by its share of TVS or its blast radius. A green core does not rescue an orange/red sub-module; conversely, a small red sub-module with capped TVS may bound the overall grade to orange. Name each module by its on-chain factory or router address. If you do not know whether a module exists, that is an unknowns[] entry, not silence. EXPLICIT TVS WEIGHTING: in the verdict, state each module's approximate share of total protocol TVS (use "~X%" if exact figures unavailable; check DeFiLlama or block-explorer balances on the module's main contract) and how that share informs the weighted grade. Format: "Module A holds ~X% of TVS (grade: <g>); Module B holds ~Y% (grade: <g>); weighted overall = <grade> because <reason>." If a red sub-module holds <5% of total TVS and is capped, the overall grade may be orange; if it holds >25%, the overall grade is red. Do not let qualitative reasoning substitute for the percentages — write the numbers.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- A1. External contract calls. Enumerate every external contract the core contracts call or read from (oracles, price feeds, AMM pools, lending pools, staking/deposit contracts, yield wrappers). For each, identify the address, the provider, and what user-facing function of this protocol would break or mis-price if that external contract paused, mis-reported, or behaved adversarially. Grep for "oracle", "aggregator", "getPrice", "latestAnswer", "chainlink", "pyth", "redstone" as a starting point. To verify an oracle is live and what it currently reports, hit https://defipunkd.com/api/contract/read?chainId=<id>&address=<oracle>&method=latestAnswer (or &method=latestRoundData, &method=getPrice, &method=description; use the BARE method name without parens) and cite the URL — the response includes blockNumber/blockHash and rawReturnData, which is stronger evidence than a docs page about which feed "should" be used.
- A2. Off-chain actor committees reporting INTO the protocol. Oracle committees, guardian multisigs, DAO-selected validator sets acting as protocol reporters, exit-bus signers, fraud-proof challengers. For each, record committee size, quorum, who picks the members, and what mis-reporting could do (mint, burn, finalize withdrawal, freeze). Distinguish this from governance admins (control slice). NOTE ON STAKING PROTOCOLS: validator slashing and node-operator misbehavior are properties of the base-chain substrate, NOT external dependencies, when the operator set is diversified enough that a coordinated failure caps at <5% principal loss. Count validator/operator risk under A2 ONLY if the operator set is small, non-diversified, or lacks bonding / slashing-insurance / diversification mitigations. A curated set of 30+ independent operators with documented diversification falls under the mitigated path; a 3-operator LST does not. Do not cite the protocol's own risk disclosure as evidence that operator failure = principal loss unless you also check the diversification and bond mitigations.
- A3. Bridge / cross-chain messaging dependencies. Only count bridges that carry material TVL or are required for a core user flow. For each, name the bridge operator (canonical L1↔L2, LayerZero, Wormhole, Axelar, custom multisig), the trust model (canonical, optimistic, light-client, guardian set), and what fraction of TVL or users ride on it. "wstETH exists on 15 chains" is not a finding unless material TVL sits there. Before listing any non-primary chain deployment as a dependency, verify it is still operational as of analysis_date — retired or sunset deployments (e.g., Lido-on-Terra, Lido-on-Solana) belong in unknowns[] or should be omitted, never cited as a current dependency.
- A4. Nested collateral / restaking chains. For restaking / LRT / receipt-of-receipt designs: record the depth of the collateral chain, every actor with slashing or freezing power at each level, and whether a failure N levels deep propagates to user principal here.
- A5. Fork lineage (silent check). If DeFiLlama's forkedFrom is non-empty, record it as one finding and move on. If empty, do NOT add a placeholder finding; it adds noise.
- A6. Fallback mechanisms and circuit breakers. What catches an external failure? Sanity-check contracts on oracle reports, rebase bounds, pause paths triggered by bad prices, second-opinion oracles, max-per-block throughput caps, withdrawal queues that absorb bad reports. Record which A1–A4 risks are mitigated by which fallback, and which are unmitigated. For EACH fallback you cite, state its activation status explicitly: (i) LIVE and enforcing on-chain today, (ii) DEPLOYED but not yet wired / activated (e.g., interface exists but the address is zero or the role is unassigned), or (iii) DOCUMENTED / PROPOSED only (forum post, LIP draft, audit pending). Only (i) counts as mitigation for the grade. A fallback in state (ii) or (iii) should be noted but must not reduce the risk in your steel-man or verdict. If you cannot determine activation status, add an unknowns[] entry rather than assume it is live.
- A7. Sequencer / L1-liveness dependency BEYOND the base-chain substrate. SCOPE — sequencer risk only counts here when the protocol IS its own L2/L3 appchain or app-rollup, where the sequencer is part of the protocol's own stack and a freeze is a protocol-level outage. A protocol permissionlessly deployed on a third-party L2 inherits that L2's sequencer as substrate, not an A7 dependency. Record the sequencer/DA trust model when A7 applies.
- A8. Keeper / relayer / off-chain bot liveness. Protocols that need permissionless-but-necessary off-chain actors (liquidation bots, auto-compounders, deposit relayers, intent solvers). Record whether the role is permissionless, what degrades if nobody runs it (yield paused, bad debt accumulates, positions go stale), and whether the failure mode is graceful or catastrophic.
- A9. Governance-mutable dependency surface. Can an admin or DAO action silently INTRODUCE a NEW EXTERNAL dependency — swap the oracle address to a different provider, register a new staking module that calls an untrusted contract, add a new bridge, route SY through a new external vault — without an exit window for users? Check the upgrade / router / module-registry contracts. Answer: which EXTERNAL dependencies are governance-mutable, who holds that power, and whether there is a timelock or exit window. SCOPE LIMIT — read carefully: A9 is about the *external dependency surface*, not the upgrade surface in general. "The proxyAdmin / EOA can upgrade the router implementation to arbitrary bytecode" is a CONTROL-slice finding (admin can rug), NOT an autonomy-A9 finding. A9 fires only when the upgrade specifically swaps out or adds a contract that THIS protocol calls or trusts (e.g., changing the oracle address from Chainlink to a malicious feed, registering a new SY adapter that points to a third-party vault, redirecting a bridge endpoint). If the only finding is "admin can change implementation," do not log it under A9 and do not let it drive the autonomy grade — note it under control instead. The autonomy-relevant version of the same upgrade key is "admin can swap [specific external address X] without timelock"; that requires identifying the specific external dependency that becomes mutable.

STEEL-MAN (per Hard Rule 13): write one-sentence strongest arguments for red, orange, and green using the A1–A9 findings.

IMPACTED TVS ESTIMATE: the headline MUST include a rough impacted-TVS figure — the fraction of protocol TVS that could be lost or frozen if the worst-unmitigated dependency you identified failed. Use "~X%" if exact numbers are unavailable, "<1%" for de minimis, "unclear" only if A1–A9 left the question genuinely open (in which case grade=unknown is usually correct). Do NOT substitute qualitative phrases like "significant" — give a number or bracket.

GRADE ANCHORS (mapped to DefiScan v1 stages):
- green = Stage 2 equivalent. Failure of any external dependency cannot cause loss of user principal or unclaimed yield. Either there are no material external dependencies, or every critical one has a documented fallback (A6) that keeps users whole. Governance cannot silently introduce new dependencies without an exit window (A9). Impacted TVS under any single-dependency failure: effectively 0.
- orange = Stage 1 equivalent. Failure of some external dependency can cause loss of unclaimed yield, or can materially change expected performance (pause withdrawals, freeze positions, degrade price quality), but cannot cause loss of principal. Committee-based oracles with sanity checks, canonical-only bridges, fallback paths that exist but are incomplete, or governance-mutable dependencies protected by a ≥7-day timelock. Impacted TVS is bounded and recoverable.
- red = Stage 0 equivalent. Failure of an external dependency CAN cause theft or loss of principal. Examples: single-provider oracle with no sanity check or fallback, material TVL on a non-canonical bridge with a guardian multisig, governance can hot-swap oracles or add staking modules with no timelock or exit window, unmitigated keeper-liveness dependency where positions become insolvent if bots stop. Impacted TVS is material.
- unknown = checklist incomplete after inspecting source + verified contracts. Prefer unknown over guessing when A1/A6 could not be reconstructed. RESERVE unknown for cases where the CORE ARCHITECTURE itself is unverifiable — not for cases where you merely cannot enumerate every per-market dependency in a multi-market protocol. If the core router/factory/oracle architecture is verifiable on-chain and you can determine whether the core requires external dependencies, grade the architecture even when an exhaustive per-market external-dependency census is infeasible. Acknowledge the per-market gap in unknowns[] but still issue a grade. Refusing to grade a multi-market protocol because you cannot list every SY/vault/market is over-use of unknown; grade the architecture and say so.

PROMPT-META CHECK (per Hard Rule 17): before finalizing, verify the verdict cites concrete contract addresses, docs, or code — not the rubric itself. If your verdict says "the protocol belongs to a category the rubric marks red", rewrite it with the A1–A9 finding that actually justifies the grade, or drop to grade=unknown.

---

### Slice: OPEN-ACCESS

Evaluate who is allowed to use the protocol and whether any of that permission is granted off-chain.

Scope: this slice is about ADMISSION — who can enter, exit, or transact. Operator LIVENESS (what breaks if keepers/oracles go offline) is assessed in the dependencies slice and is out of scope for the grade here. You may note operator dependencies as context, but do not let "the protocol halts if operator X disappears" drive the access grade on its own; that belongs in dependencies. Source verification / contract verification on block explorers is assessed in the verifiability slice and is out of scope here — do NOT let "contract is unverified" drive the access grade.

Framing: the smart contracts are the access layer; frontends are UX. A permissionless contract is reachable by any client (SDK, third-party UI, aggregator, wallet integration). Frontend ToS, IP geo-blocking, and wallet screening are publisher policies on one specific client — they are reported as context but do NOT determine the grade. The grade hinges on (1) what the contract itself permits, and (2) whether the protocol is practically reachable without the official publisher's cooperation.

Meta-check before finalizing: if your verdict cites phrases from this prompt as evidence ("the protocol meets the 'credible alternatives' condition", "this fits the 'documented fallback' rule"), redo the verdict. The prompt describes the rubric; evidence must come from the protocol. A verdict should cite what the protocol does, not what the rubric says.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- A1. Whitelist / allowlist modifiers in user-facing entry points. Grep for "onlyWhitelisted", "onlyRole", "allowlist", "isAccredited", "isKYCed". Note which functions are gated and who can add/remove from the list.
- A2. Off-chain operators in the admission path: keepers, sequencers, privileged relayers, oracle posters whose approval is required to admit a user action (not just to keep the protocol live). For each, identify whether the role is held by a single operator, a permissioned committee, or is permissionless. Enumerate per user-facing function class (deposit vs withdraw-request vs claim-finalized vs transfer) which ones require operator approval to be admitted, and which ones admit users unconditionally. A function whose placement is unconditional but whose downstream settlement depends on an operator is an admission-permissionless function — flag the liveness dependency as context and defer its grading weight to the dependencies slice.
- A3. Frontend restrictions on the official interface — record as context, not as a grade lever. Distinguish:
    - A3-passive: boilerplate ToS clauses (sanctions attestation, restricted-territory self-certification, VPN-circumvention prohibition, "comply with applicable law" eligibility, age of majority).
    - A3-active: runtime enforcement — IP-based geo-blocking, wallet-address screening against a sanctions oracle (Chainalysis, TRM, Elliptic), KYC wall, rendering-blocking jurisdiction banner.
  Record findings under the correct tier. Quote ToS text or banner text in evidence[].shows. These findings populate the headline and rationale but do NOT move the grade by themselves; the grade is set by A1, A2, and the A3b path check below.
- A3b. Independent access paths (the operative grade input). Enumerate paths that do not require the official publisher's cooperation:
    - Published SDK / library / CLI for direct contract interaction.
    - Third-party frontends operated by separate legal entities.
    - Wallet-integrated access (MetaMask Swaps, Safe apps, etc.).
    - DEX / lending / yield aggregators that route through the contracts.
  Record at least one concrete link per path that exists. The protocol does NOT have to self-document these — the test is existence, not UX cost. An A3b-i redistribution of the official UI bound by the same ToS does NOT count as an independent path.
- A4. Sanctions / compliance tooling at the contract level: does the protocol check addresses against OFAC lists or similar on-chain blocklists in the contract itself? (Frontend-only screening belongs in A3.)
- A5. Differentiate read access vs write access: many protocols are read-permissionless (anyone can view state) but write-gated (only certain addresses can deposit/borrow). Record both.
- A6. ToS / Legal links: locate them on the website and produce a VERBATIM quote of any jurisdictional, sanctions, or eligibility clause in evidence[].shows. If you cannot extract the clause text verbatim (SPA render failure, paywall, dead link, etc.), do NOT paraphrase or infer from general knowledge — record the ToS URL in unknowns[] with the reason extraction failed. Assertions about ToS content without a verbatim quote will be downweighted by reviewers.

Then write the steel-man section per Hard Rule 11.

Grade rules (admission-focused; liveness concerns belong in dependencies; source verification belongs in verifiability):
- green   = no contract-level whitelist/KYC on user entry/exit; no operator approval required to admit a user action; AND at least one independent A3b path exists (published SDK, third-party frontend, wallet integration, or aggregator routing). Frontend ToS posture and A3-active enforcement on the official UI do NOT block green when contracts are permissionless and an independent path exists — they are reported as context.
- orange  = contracts admit users unconditionally, BUT the protocol is operationally captured by the official publisher: no published SDK, no third-party frontend, no wallet integration, no aggregator routing. The contract is theoretically open but practically reachable only through the official UI. Also applies when admission requires approval from a permissioned committee that is governance-managed with a documented replacement procedure.
- red     = contract-level whitelist / KYC on user entry/exit, OR admission of a core user action requires approval from a single privileged operator or a small committee with no documented replacement procedure, OR enforces an on-chain blocklist updatable by a single party.
- unknown = checklist incomplete after checking the sources above.

Default-grade guidance: when contracts are fully permissionless AND any A3b independent path exists, the default grade is green regardless of frontend ToS or A3-active enforcement on the official UI. Frontend geo-blocking, sanctions-oracle wallet screening, and ToS sanctions clauses are publisher policies on one client and are reported in findings/headline as context, not as grade levers. To grade orange on operational-capture grounds, the auditor must affirmatively show that ALL independent paths are absent or also gated.

Guideline on committees: where admission depends on a multi-operator committee, the relevant axes are (a) set size, (b) whether replacement/rotation is governed on-chain, (c) whether the replacement procedure is publicly documented. A large set with on-chain governance replacement should not be graded as a single-party operator even if rotation is not instantaneous. A small set with informal replacement should be treated as a single-party operator.

---

### Slice: VERIFIABILITY

Evaluate whether an outsider can independently confirm what the deployed code does.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- V1. For each address you assess: is the bytecode verified on the chain's block explorer? Record the "Contract Source Code Verified" indicator. https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x... returns this as a top-level "verified" boolean plus "abiSource" ("etherscan" / "sourcify") and an inline ABI — useful when the explorer page is rate-limited. If the contract is a proxy, verify BOTH the proxy contract AND the current implementation contract. The same /api/contract/abi response auto-resolves proxies and includes a "proxy.implementation" address when present, so one call covers V1 + V6 in one shot. An explorer "Similar Match" on a well-known proxy pattern (Aragon AppProxyUpgradeable, ERC1967Proxy, OssifiableProxy, OZ TransparentUpgradeableProxy) is expected for that pattern and does NOT count as a verification gap on its own — what matters is that the implementation is independently verified.
- V2. Source-to-repo correspondence: for each verified contract, attempt to find a matching commit in the linked GitHub repos. Record evidence[].commit on a match. Independent compile/bytecode-match is NOT required for green — a recognized public repo whose structure and file contents correspond to the explorer-visible source is sufficient. If you did not pin a commit SHA or run a bytecode diff, record that plainly in unknowns[] and proceed; it is a scope limit, not a downgrade signal.
- V3. Audit coverage: for each URL in protocol.audit_links, open it and record: auditor name, audit date, the specific contracts / commit in scope. Flag audits that predate the current deployment by >6 months without a follow-up review.
- V4. Auditor recognition: the following firms are broadly recognized in Solidity: Trail of Bits, Zellic, Spearbit, OpenZeppelin, ConsenSys Diligence, Certora (formal verification), Quantstamp, Halborn, Peckshield, Sigma Prime, ChainSecurity, Ackee Blockchain, MixBytes, Statemind. Unknown firms are orange-at-best for any green-grade claim. Name the firm explicitly in evidence[].
- V5. Post-audit drift: compare the most recent in-scope audit(s) against the currently-deployed source, weighted by what each contract does and by what the changes actually contain. SCOPE — drift only downgrades the grade when ALL of the following hold: (i) the drifting contract is fund-custody / settlement / accounting-critical (NOT a peripheral router, lens, quoter, or pure-view contract that holds no balances); (ii) the changes are material — new functions, modified access control, modified accounting, modified fund flow — and not refactors / struct relocations / import reorgs / build or CI fixes / formatting; (iii) no later audit, fix-audit, or differential audit from a recognized firm covers the changed files (audits often pin a pre-fix commit while a follow-up reviews the delta — match by file scope, not by commit-hash equality). When you cite drift as a downgrade reason, name the specific behavior change (function added, role granted, accounting formula altered) — "N commits ahead" or "+X/-Y LOC" alone is not evidence of material drift. If you have not sampled the diff content (e.g. via the GitHub compare view or the top commits in the window), record drift as an unknowns[] entry rather than auto-downgrading; commit-count and LOC are starting signals, not findings.
- V6. Implementation vs proxy: a verified proxy with an unverified implementation is effectively unverified. State whether the implementation is verified separately.

EVIDENCE DISCIPLINE (read before writing findings[]):
- Do not assert a specific deploy-commit SHA, bytecode equivalence, or "identical to audited commit" unless you actually fetched the artifact that shows it (e.g., a deployed-addresses JSON you opened, an explorer page you read). Inferred or plausible matches belong in unknowns[], never in findings[] or evidence[].
- Evidence[] entries must correspond to pages/files you actually retrieved this run. A URL you did not open is not evidence.

Then write the steel-man section per Hard Rule 11.

Grade rules:
- green   = deployed bytecode verified on the explorer (proxy AND implementation if proxied; "Similar Match" on a standard proxy pattern is fine per V1), a public source repo exists whose contents correspond to the explorer-visible source, AND ≥1 audit from a recognized firm covering the currently-deployed contracts (≤6 months of drift OR drift was re-audited). A missing local compile-match is not a downgrade — record it in unknowns[] and still grade green if the other conditions hold.
- orange  = verified but with visible drift from the public repo, OR audit scope is stale relative to deployment, OR only minor / unknown-firm audits exist, OR only some of the main contracts are verified, OR proxy verified but implementation only partially verified.
- red     = unverified bytecode (or verified proxy with unverified implementation), OR no audit in protocol.audit_links, OR no public repo.
- unknown = reserved for when the protocol's verifiability posture genuinely cannot be assessed (e.g., explorer and repo both inaccessible for this protocol). Do NOT use unknown merely because you, the analyst, could not run a particular check such as a bytecode diff — that goes in unknowns[] while the grade is still assigned from the evidence you do have.

---

### JSON output contract

Return exactly one JSON array inside a single ```json fenced block. The array MUST contain exactly five objects, one per risk slice, in this exact order: "control", "ability-to-exit", "autonomy", "open-access", "verifiability". Do not include the discovery slice.

Each object has the same shape as a normal slice submission:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "<one of: control | ability-to-exit | autonomy | open-access | verifiability>",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- Produce one complete object for each of these slices only: control, ability-to-exit, autonomy, open-access, verifiability.
- Reuse the same model, chat_url, snapshot_generated_at, prompt_version, analysis_date, and slug values across all five objects.
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches that object's slice checklist prefix verbatim (C1, E2, AU3, A3b, V4a, …); unknowns[] entries are checklist-coded ("C3: …").
- Wrap the array in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Verifiability tentative

No public repo or audits

Neither a GitHub repository nor any audit is recorded. At Phase 0 this is the most conservative verifiability signal DeFiPunk'd can assign.

Run your own prompt Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-us
- protocol.name:              Polymarket US
- protocol.chains:            (none recorded)
- protocol.category:          Prediction Market
- protocol.website:           https://polymarketexchange.com/
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               null

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
(no addresses pinned in this run — discover candidates from fetched website / GitHub / audit / explorer pages, record discovered addresses in evidence[] and protocol_metadata.admin_addresses, and put any reads you couldn't perform in unknowns[]. The next assessment will inherit your discoveries.)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: VERIFIABILITY

Evaluate whether an outsider can independently confirm what the deployed code does.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- V1. For each address you assess: is the bytecode verified on the chain's block explorer? Record the "Contract Source Code Verified" indicator. https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x... returns this as a top-level "verified" boolean plus "abiSource" ("etherscan" / "sourcify") and an inline ABI — useful when the explorer page is rate-limited. If the contract is a proxy, verify BOTH the proxy contract AND the current implementation contract. The same /api/contract/abi response auto-resolves proxies and includes a "proxy.implementation" address when present, so one call covers V1 + V6 in one shot. An explorer "Similar Match" on a well-known proxy pattern (Aragon AppProxyUpgradeable, ERC1967Proxy, OssifiableProxy, OZ TransparentUpgradeableProxy) is expected for that pattern and does NOT count as a verification gap on its own — what matters is that the implementation is independently verified.
- V2. Source-to-repo correspondence: for each verified contract, attempt to find a matching commit in the linked GitHub repos. Record evidence[].commit on a match. Independent compile/bytecode-match is NOT required for green — a recognized public repo whose structure and file contents correspond to the explorer-visible source is sufficient. If you did not pin a commit SHA or run a bytecode diff, record that plainly in unknowns[] and proceed; it is a scope limit, not a downgrade signal.
- V3. Audit coverage: for each URL in protocol.audit_links, open it and record: auditor name, audit date, the specific contracts / commit in scope. Flag audits that predate the current deployment by >6 months without a follow-up review.
- V4. Auditor recognition: the following firms are broadly recognized in Solidity: Trail of Bits, Zellic, Spearbit, OpenZeppelin, ConsenSys Diligence, Certora (formal verification), Quantstamp, Halborn, Peckshield, Sigma Prime, ChainSecurity, Ackee Blockchain, MixBytes, Statemind. Unknown firms are orange-at-best for any green-grade claim. Name the firm explicitly in evidence[].
- V5. Post-audit drift: compare the most recent in-scope audit(s) against the currently-deployed source, weighted by what each contract does and by what the changes actually contain. SCOPE — drift only downgrades the grade when ALL of the following hold: (i) the drifting contract is fund-custody / settlement / accounting-critical (NOT a peripheral router, lens, quoter, or pure-view contract that holds no balances); (ii) the changes are material — new functions, modified access control, modified accounting, modified fund flow — and not refactors / struct relocations / import reorgs / build or CI fixes / formatting; (iii) no later audit, fix-audit, or differential audit from a recognized firm covers the changed files (audits often pin a pre-fix commit while a follow-up reviews the delta — match by file scope, not by commit-hash equality). When you cite drift as a downgrade reason, name the specific behavior change (function added, role granted, accounting formula altered) — "N commits ahead" or "+X/-Y LOC" alone is not evidence of material drift. If you have not sampled the diff content (e.g. via the GitHub compare view or the top commits in the window), record drift as an unknowns[] entry rather than auto-downgrading; commit-count and LOC are starting signals, not findings.
- V6. Implementation vs proxy: a verified proxy with an unverified implementation is effectively unverified. State whether the implementation is verified separately.

EVIDENCE DISCIPLINE (read before writing findings[]):
- Do not assert a specific deploy-commit SHA, bytecode equivalence, or "identical to audited commit" unless you actually fetched the artifact that shows it (e.g., a deployed-addresses JSON you opened, an explorer page you read). Inferred or plausible matches belong in unknowns[], never in findings[] or evidence[].
- Evidence[] entries must correspond to pages/files you actually retrieved this run. A URL you did not open is not evidence.

Then write the steel-man section per Hard Rule 11.

Grade rules:
- green   = deployed bytecode verified on the explorer (proxy AND implementation if proxied; "Similar Match" on a standard proxy pattern is fine per V1), a public source repo exists whose contents correspond to the explorer-visible source, AND ≥1 audit from a recognized firm covering the currently-deployed contracts (≤6 months of drift OR drift was re-audited). A missing local compile-match is not a downgrade — record it in unknowns[] and still grade green if the other conditions hold.
- orange  = verified but with visible drift from the public repo, OR audit scope is stale relative to deployment, OR only minor / unknown-firm audits exist, OR only some of the main contracts are verified, OR proxy verified but implementation only partially verified.
- red     = unverified bytecode (or verified proxy with unverified implementation), OR no audit in protocol.audit_links, OR no public repo.
- unknown = reserved for when the protocol's verifiability posture genuinely cannot be assessed (e.g., explorer and repo both inaccessible for this protocol). Do NOT use unknown merely because you, the analyst, could not run a particular check such as a bytecode diff — that goes in unknowns[] while the grade is still assigned from the evidence you do have.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "verifiability",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

4 dimensions not yet assessed (Control, Ability to exit, Autonomy, Open Access)

Control unknown Unverified

Not yet assessed

Who holds admin privileges, how contracts can be upgraded, and how quickly. No automated heuristic grades this at Phase 0; a real assessment arrives when onchain discovery reads roles, owners, and timelocks.

No model has graded this dimension yet. Run the slice prompt through any LLM and submit the JSON — once ≥3 independent runs agree, the quorum bot merges the verdict here.

Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-us
- protocol.name:              Polymarket US
- protocol.chains:            (none recorded)
- protocol.category:          Prediction Market
- protocol.website:           https://polymarketexchange.com/
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               null

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
(no addresses pinned in this run — discover candidates from fetched website / GitHub / audit / explorer pages, record discovered addresses in evidence[] and protocol_metadata.admin_addresses, and put any reads you couldn't perform in unknowns[]. The next assessment will inherit your discoveries.)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: CONTROL

Evaluate who can change the protocol's rules, how fast, and how broadly.

(Step 0 capability probe and the off-chain-only fallback live in the preamble — those rules apply here.)

### MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[])

- **C1.** For each address you assess: who is the contract owner / admin / pendingAdmin / governor — read these via the block explorer's "Read Contract" tab OR `https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=owner` (BARE method names: `&method=owner`, `&method=admin`, `&method=pendingOwner`, `&method=governor`). For Safes use `/api/safe/owners?chainId=<id>&address=0x...`. When a protocol has multiple major versions deployed (v2/v3/v4), perform C1 reads on the NEWEST deployment separately — newer deployments often have weaker control surfaces than the legacy core.
- **C2.** Upgrade mechanism: transparent proxy / UUPS / Beacon / Diamond / immutable. Identify the proxy admin address. Check upgradeability of GOVERNANCE contracts too — a Governor / Aragon Voting / OZ Governor is often itself a proxy whose admin is the Timelock. Asymmetry: when fund-holding cores are immutable AND governance has no admin path that reaches them, an upgradable Governor/Timelock is T3-only and must NOT drag the verdict below green on that basis alone (see grade rules and the "immutable cores" caveat). Only call upgradability "mixed" if you can name a concrete function on the upgradable surface that reaches T1 or T2 on user funds.
- **C3.** EXECUTION PATH (enumerate every stage, in order, with delays in seconds). The operative path is usually a chain (voting → scheduler → timelock → executor; or governor → queue → execute; or Aragon Voting → DualGovernance → EmergencyProtectedTimelock → AdminExecutor). For each stage, record (a) the contract address, (b) the delay constant name + value in seconds, (c) the URL you read it from (block-explorer Read Contract OR `/api/contract/read?...&method=MIN_DELAY&block=<n>`). Do NOT stop at the first timelock-shaped contract — if its admin is itself called by another contract, keep walking. The grading delay is the SUM OF DELAYS ON THE UNCONTESTED FAST PATH (shortest time a proposal with no opposition can go from submission to executable). Dynamic / contested extensions (veto signaling, rage quit, escrow delay) are modifiers, not the basis — note them separately.
- **C4.** Enumerate EVERY multisig with reachable control — main proxy admin, emergency activation, emergency execution, reseal / pause, gate-seal committees, tiebreaker, per-module admins. For each Safe, fetch threshold + owners + version via `/api/safe/owners?chainId=<id>&address=0x...` (response includes raw eth_call data, so the URL is citable evidence). Enumerate ops/council/incentives multisigs even when off the upgrade path — record their scope so a reader can see they are NOT on the upgrade path. For each: (a) address, (b) threshold / total signers, (c) signer identities classified as insider (team, paid auditors under ongoing engagement, mandated service providers) vs non-insider (independent community members, unaffiliated researchers), (d) the specific power held (upgrade, pause, parameter, etc.).
- **C5.** On-chain governance: Governor / GovernorBravo / OZ Governor / Aragon Voting with token-weighted voting? Record proposal threshold, voting period, quorum, and the timelock delay between queue and execute. Every numeric constant must come from a Read Contract call you can link to, or be in unknowns[] with the C-code. If votingDelay / votingPeriod are denominated in BLOCKS, convert to seconds at the chain's CURRENT block time (Ethereum mainnet ≈ 12s post-Merge, not the 15s in older Compound/Bravo deployments) — cite both block count and converted seconds.
- **C6.** EMERGENCY POWERS: separate emergency-pause / guardian role with a different time cap or different actor than the main upgrade authority? Record it explicitly.
- **C7.** POWER TIER (blast radius). For each privileged path in C3–C6, classify the WORST thing that path can do, choosing the highest applicable tier. Cite the specific function name and any on-chain bound — tier claims without a named function are unsupported.
    - **T1 — FUND-CRITICAL**: replace implementation of contracts holding user funds; change AMM math / accounting / collateral logic; mint unbacked debt or shares; pause withdrawals; drain user-fund treasury; change oracle to attacker-controlled source; replace upgrade admin with EOA.
    - **T2 — ECONOMICALLY MATERIAL**: change fee parameters within bounded ranges; redirect protocol fees; add/remove markets / collateral types; bounded inflation or token mint within hard-capped schedule; spend protocol-owned (non-user) treasury.
    - **T3 — GOVERNANCE-INTERNAL**: change voting rules, quorum, voting period, proposal threshold; upgrade the Governor itself; rotate Timelock admin; mint governance tokens within a capped annual schedule.
    - **T4 — OPERATIONAL**: incentives distribution, grants, ENS / frontend canonicalization, deployment coordination, periphery router deprecation.
  The grade is set by the HIGHEST tier reachable on the uncontested fast path, not the median. State the tier and the binding function in the verdict.

### Read Contract discipline (applies to C3, C4, C5)

Every numeric constant cited (timelock delays, voting periods, multisig thresholds, quorum percentages) must come from EITHER (a) a block-explorer Read Contract URL, OR (b) a DeFiPunkd `/api/contract/read` or `/api/safe/owners` URL (preferred with `&block=<n>` for content-addressed evidence), OR (c) an unknowns[] entry with the C-code. Docs / blog posts are corroboration only — they cannot be the sole citation for a value that is also readable on-chain.

### Off-chain-only substitute hierarchy (when grading_basis="off-chain-only" — see preamble Rule 16)

When on-chain reads were genuinely unreachable this run, eligible off-chain substitutes in priority order:
1. Linked audit PDFs (admin roles, multisig members, timelock delays usually enumerated).
2. Governance forum posts that quote constants from a successful on-chain proposal (cite post URL + linked execution-tx URL).
3. Official protocol docs pages with named addresses and roles (must be on a domain owned by the protocol).
4. GitHub README / SECURITY.md / governance/*.md at a pinned commit SHA.

Forbidden substitutes: third-party blog posts, X / Twitter threads, search-result snippets, model memory. Required degradation: any C-code citing a numeric constant from docs/forum/audit prose ONLY must also carry an `unknowns[]` entry with `-offchain` suffix noting "value not re-read on-chain in this run; corroboration only".

### Grade rules (apply the timelock bar conditional on the highest C7 tier reachable on the fast path)

Security Council standard (used below): a multisig qualifies as "Security Council" only if ALL of: ≥7 signers, ≥51% threshold, ≥50% non-insider signers, every signer publicly announced. Failing any criterion = NOT a Security Council, regardless of signer reputation.

- **green**: highest reachable tier is T3 or T4 regardless of timelock; OR T2 reachable with uncontested-fast-path delay ≥7 days; OR T1 reachable only via immutable contracts (T1 is unreachable); OR T1 reachable with uncontested-fast-path delay ≥7 days combined with a Security Council multisig; OR T1 reachable with uncontested-fast-path delay ≥7 days through active on-chain governance with broad token distribution.
- **orange**: T2 reachable with uncontested-fast-path delay >0 but <7 days; OR T1 reachable with uncontested-fast-path delay >0 but <7 days; OR a multisig failing one or more Security Council criteria sits on a T1/T2 path; OR unclear upgrade authority on a T1/T2 path; OR governance with very short timelock or low quorum on a T1/T2 path.
- **red**: T1 reachable with no timelock by a single EOA or 2-of-3 multisig; OR a T1 upgrade admin that is not a smart contract you can audit.
- **unknown**: completed the checklist but still cannot determine the upgrade authority OR cannot classify the highest tier reachable on the main contracts.

Tiering caveats:
- "Bounded" must be enforced ON-CHAIN to count as T2. A function that sets fees with no upper-bound check is T1 — cite the bound check.
- Recurring T2 economic extraction (e.g. fee redirect with no rate limit) approaches T1 over time. A single proposal that can permanently redirect all future revenue is T1.
- T3 assumes the governance contract cannot itself authorize a T1/T2 action without going through the same timelock. If governance can self-upgrade to bypass the timelock, T3 collapses into T1.
- Do not downgrade tier by hand-waving ("realistically governance would never…"). Tier on what the contract permits, not what feels likely.

Notes:
- **Dynamic / dual-governance timelocks** (Lido, Compound escrow veto): the rubric grades on the uncontested path because that is the path most upgrades take. A dynamic extension that fires only under stake-weighted opposition is a real protection — name it in the green steel-man, but it does not lift an orange fast path into green; state the tension in the verdict.
- **Immutable cores with upgradable governance** (Uniswap-style): if fund-holding contracts are immutable and have no admin-reachable function moving / freezing / re-routing user funds, the highest reachable tier on the upgrade path is T3 — green regardless of timelock. Don't grade this orange just because the Governor is a proxy — that's a C2 fact, not a downgrade. Downgrade only applies if you can cite a concrete function on the upgradable surface that reaches T1 or T2 (privileged hook, upgradable factory controlling fund-routing, fee-switch redirecting protocol revenue without bound).
- **The 7-day bar** reflects the exit-window standard — users need notice after a queued upgrade to withdraw if they disagree. The ability-to-exit slice grades the exit side; this slice grades the delay side; both must hold for users to actually benefit from the delay.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "control",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Ability to exit unknown Unverified

Not yet assessed

Whether users can exit on their own terms if the team disappears or acts adversarially. Requires per-protocol review; not available at Phase 0.

No model has graded this dimension yet. Run the slice prompt through any LLM and submit the JSON — once ≥3 independent runs agree, the quorum bot merges the verdict here.

Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-us
- protocol.name:              Polymarket US
- protocol.chains:            (none recorded)
- protocol.category:          Prediction Market
- protocol.website:           https://polymarketexchange.com/
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               null

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
(no addresses pinned in this run — discover candidates from fetched website / GitHub / audit / explorer pages, record discovered addresses in evidence[] and protocol_metadata.admin_addresses, and put any reads you couldn't perform in unknowns[]. The next assessment will inherit your discoveries.)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: ABILITY-TO-EXIT

Evaluate whether users can withdraw their funds on their own terms, even under adversarial admin conditions.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- E1. Enumerate every user-facing exit function in the main contracts: withdraw, redeem, burn, requestWithdrawal, claim, exit, etc. List them by name. Do NOT treat the contract as a monolith.
- E2. For EACH exit function in E1: identify its access modifiers and any pause guards (e.g. _checkResumed, whenNotPaused, onlyRole). Functions that gate REQUEST PLACEMENT often differ from functions that CLAIM FINALIZED FUNDS — check both separately.
- E3. For each pause guard: identify the role holder (which address holds PAUSE_ROLE / GUARDIAN / etc.) and the maximum pause duration. Specifically check whether PAUSE_INFINITELY (or equivalent uncapped pause) is callable, and which actor can call it (single multisig vs governance vote). For role-holder reads use https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=hasRole&args=0x...,0x... or &method=getRoleAdmin&args=0x.... For "is currently paused" checks use &method=paused or &method=isPaused&args=<resume-code>. Use the BARE method name (no parens). Cite the URL with &block=<n> in evidence[].
- E4. EMERGENCY vs GOVERNANCE pause distinction: many protocols have a fast-acting emergency pause capped at N days and a slow governance pause that can be indefinite. Record both paths separately if present, with their time caps and actor classes.
- E5. Queued redemption: documented maximum queue duration, daily withdrawal caps, whether the queue itself is pausable.
- E6. Forced-exit / escape-hatch / permissionless emergency-exit mechanism for adversarial-admin scenarios.
- E7. Frontend dependency: confirm exit functions are directly callable on-chain (e.g. via Etherscan write tab or a generic wallet) without the project's frontend.

Then write the steel-man section per Hard Rule 11. Common red-vs-orange tension on this slice: indefinite pause exists (suggests red) BUT the realistic emergency path is time-capped AND claims of already-finalized exits are not pause-gated (suggests orange). Resolve this by stating who can do what for how long, not by stopping at the worst-case sentence.

Grade rules:
- green   = permissionless exit; pause is either absent, narrowly scoped to clearly-described emergencies with auto-expiry, or capped at ≤7 days; no frontend dependency for exit; claims of already-finalized exits are not pause-gated under any path.
- orange  = pausable with broad scope OR indefinite pause is reachable only through governance vote (not unilateral admin action), OR queued redemption with documented max > 7 days, OR claims-of-finalized are exempt but new-request placement can be paused indefinitely by governance.
- red     = exit requires admin signature, OR ANY actor (including governance) can pause CLAIMS of finalized exits indefinitely, OR there is no on-chain exit function at all (purely custodial), OR pause is held by a single EOA / 2-of-3 multisig with no time cap.
- unknown = checklist incomplete after checking the sources above.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "ability-to-exit",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Autonomy unknown Unverified

No Phase-0 autonomy signal

Neither the category heuristic nor the forkedFrom signal fires for this protocol. A real autonomy graph (oracles, bridges, fallbacks, governance-mutable dependencies) arrives with Phase-2 onchain discovery.

No model has graded this dimension yet. Run the slice prompt through any LLM and submit the JSON — once ≥3 independent runs agree, the quorum bot merges the verdict here.

Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-us
- protocol.name:              Polymarket US
- protocol.chains:            (none recorded)
- protocol.category:          Prediction Market
- protocol.website:           https://polymarketexchange.com/
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               null

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
(no addresses pinned in this run — discover candidates from fetched website / GitHub / audit / explorer pages, record discovered addresses in evidence[] and protocol_metadata.admin_addresses, and put any reads you couldn't perform in unknowns[]. The next assessment will inherit your discoveries.)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: AUTONOMY

Evaluate this protocol's autonomy: can a failure of anything outside its own contracts cause theft or loss of user principal, loss of unclaimed yield, or materially change the protocol's expected performance? "Autonomy" is not "has zero external touchpoints" — it is "external failures are either survivable or recoverable without user loss". This slice adapts DefiScan v1's Autonomy dimension; dependencies are one of several criteria, not the whole frame.

GUARDRAILS (read before grading):
- Category alone (Liquid Staking, Bridge, RWA Lending, Restaking, …) does NOT force a grade. A category is a hint about where to look; the grade must come from the concrete A1–A9 findings below.
- Base-chain consensus (Ethereum PoS, the chain's validator set, the canonical Deposit Contract at 0x00000000219ab540356cBB839Cbe05303d7705Fa) is the SUBSTRATE, not a dependency, for any protocol deployed on that chain. Do not list "depends on Ethereum" as a finding.
- Oracles or other integrations used by DOWNSTREAM protocols that happen to read this protocol's token (e.g. Chainlink stETH/USD consumed by Aave) are NOT this protocol's dependencies. Count only what THIS protocol's contracts call or trust on-chain. If a feed or contract appears in the protocol's docs only as reference material for third-party integrators, EXCLUDE IT ENTIRELY — do not log it as a finding even with a "peripheral" or "referenced only" caveat.
- "Upgradeable admin can change things" belongs to the CONTROL slice; only count it here when the upgrade surface lets governance silently swap an external dependency (see A9).
- Underlying-asset risk in opt-in, isolated markets is NOT autonomy-red on its own. When a protocol wraps third-party yield-bearing assets (LSTs, LRTs, ERC-4626 vaults, lending receipts, restaked tokens) into per-market silos that users explicitly choose, a failure of one underlying does NOT propagate to other markets and is risk the user opted into per-market. Record it under A4 with depth and propagation scope, but do not let it alone drive a red verdict — red requires an external dependency that cross-cuts the protocol or that the user did not opt into at deposit time. A failure mode that is "if the LRT you deposited is hacked, your principal in that LRT-backed market is impaired" is the underlying's autonomy story, not this protocol's; grade it on whether THIS protocol introduces additional dependencies on top.
- Sub-module enumeration is mandatory before grading. If the protocol ships distinct product lines or modules (e.g., a v2 core AMM plus a newer perps/funding-rate module, a lending pool plus a separate vault layer, an L1 core plus a cross-chain extension), enumerate each in findings and grade against the WORST module weighted by its share of TVS or its blast radius. A green core does not rescue an orange/red sub-module; conversely, a small red sub-module with capped TVS may bound the overall grade to orange. Name each module by its on-chain factory or router address. If you do not know whether a module exists, that is an unknowns[] entry, not silence. EXPLICIT TVS WEIGHTING: in the verdict, state each module's approximate share of total protocol TVS (use "~X%" if exact figures unavailable; check DeFiLlama or block-explorer balances on the module's main contract) and how that share informs the weighted grade. Format: "Module A holds ~X% of TVS (grade: <g>); Module B holds ~Y% (grade: <g>); weighted overall = <grade> because <reason>." If a red sub-module holds <5% of total TVS and is capped, the overall grade may be orange; if it holds >25%, the overall grade is red. Do not let qualitative reasoning substitute for the percentages — write the numbers.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- A1. External contract calls. Enumerate every external contract the core contracts call or read from (oracles, price feeds, AMM pools, lending pools, staking/deposit contracts, yield wrappers). For each, identify the address, the provider, and what user-facing function of this protocol would break or mis-price if that external contract paused, mis-reported, or behaved adversarially. Grep for "oracle", "aggregator", "getPrice", "latestAnswer", "chainlink", "pyth", "redstone" as a starting point. To verify an oracle is live and what it currently reports, hit https://defipunkd.com/api/contract/read?chainId=<id>&address=<oracle>&method=latestAnswer (or &method=latestRoundData, &method=getPrice, &method=description; use the BARE method name without parens) and cite the URL — the response includes blockNumber/blockHash and rawReturnData, which is stronger evidence than a docs page about which feed "should" be used.
- A2. Off-chain actor committees reporting INTO the protocol. Oracle committees, guardian multisigs, DAO-selected validator sets acting as protocol reporters, exit-bus signers, fraud-proof challengers. For each, record committee size, quorum, who picks the members, and what mis-reporting could do (mint, burn, finalize withdrawal, freeze). Distinguish this from governance admins (control slice). NOTE ON STAKING PROTOCOLS: validator slashing and node-operator misbehavior are properties of the base-chain substrate, NOT external dependencies, when the operator set is diversified enough that a coordinated failure caps at <5% principal loss. Count validator/operator risk under A2 ONLY if the operator set is small, non-diversified, or lacks bonding / slashing-insurance / diversification mitigations. A curated set of 30+ independent operators with documented diversification falls under the mitigated path; a 3-operator LST does not. Do not cite the protocol's own risk disclosure as evidence that operator failure = principal loss unless you also check the diversification and bond mitigations.
- A3. Bridge / cross-chain messaging dependencies. Only count bridges that carry material TVL or are required for a core user flow. For each, name the bridge operator (canonical L1↔L2, LayerZero, Wormhole, Axelar, custom multisig), the trust model (canonical, optimistic, light-client, guardian set), and what fraction of TVL or users ride on it. "wstETH exists on 15 chains" is not a finding unless material TVL sits there. Before listing any non-primary chain deployment as a dependency, verify it is still operational as of analysis_date — retired or sunset deployments (e.g., Lido-on-Terra, Lido-on-Solana) belong in unknowns[] or should be omitted, never cited as a current dependency.
- A4. Nested collateral / restaking chains. For restaking / LRT / receipt-of-receipt designs: record the depth of the collateral chain, every actor with slashing or freezing power at each level, and whether a failure N levels deep propagates to user principal here.
- A5. Fork lineage (silent check). If DeFiLlama's forkedFrom is non-empty, record it as one finding and move on. If empty, do NOT add a placeholder finding; it adds noise.
- A6. Fallback mechanisms and circuit breakers. What catches an external failure? Sanity-check contracts on oracle reports, rebase bounds, pause paths triggered by bad prices, second-opinion oracles, max-per-block throughput caps, withdrawal queues that absorb bad reports. Record which A1–A4 risks are mitigated by which fallback, and which are unmitigated. For EACH fallback you cite, state its activation status explicitly: (i) LIVE and enforcing on-chain today, (ii) DEPLOYED but not yet wired / activated (e.g., interface exists but the address is zero or the role is unassigned), or (iii) DOCUMENTED / PROPOSED only (forum post, LIP draft, audit pending). Only (i) counts as mitigation for the grade. A fallback in state (ii) or (iii) should be noted but must not reduce the risk in your steel-man or verdict. If you cannot determine activation status, add an unknowns[] entry rather than assume it is live.
- A7. Sequencer / L1-liveness dependency BEYOND the base-chain substrate. SCOPE — sequencer risk only counts here when the protocol IS its own L2/L3 appchain or app-rollup, where the sequencer is part of the protocol's own stack and a freeze is a protocol-level outage. A protocol permissionlessly deployed on a third-party L2 inherits that L2's sequencer as substrate, not an A7 dependency. Record the sequencer/DA trust model when A7 applies.
- A8. Keeper / relayer / off-chain bot liveness. Protocols that need permissionless-but-necessary off-chain actors (liquidation bots, auto-compounders, deposit relayers, intent solvers). Record whether the role is permissionless, what degrades if nobody runs it (yield paused, bad debt accumulates, positions go stale), and whether the failure mode is graceful or catastrophic.
- A9. Governance-mutable dependency surface. Can an admin or DAO action silently INTRODUCE a NEW EXTERNAL dependency — swap the oracle address to a different provider, register a new staking module that calls an untrusted contract, add a new bridge, route SY through a new external vault — without an exit window for users? Check the upgrade / router / module-registry contracts. Answer: which EXTERNAL dependencies are governance-mutable, who holds that power, and whether there is a timelock or exit window. SCOPE LIMIT — read carefully: A9 is about the *external dependency surface*, not the upgrade surface in general. "The proxyAdmin / EOA can upgrade the router implementation to arbitrary bytecode" is a CONTROL-slice finding (admin can rug), NOT an autonomy-A9 finding. A9 fires only when the upgrade specifically swaps out or adds a contract that THIS protocol calls or trusts (e.g., changing the oracle address from Chainlink to a malicious feed, registering a new SY adapter that points to a third-party vault, redirecting a bridge endpoint). If the only finding is "admin can change implementation," do not log it under A9 and do not let it drive the autonomy grade — note it under control instead. The autonomy-relevant version of the same upgrade key is "admin can swap [specific external address X] without timelock"; that requires identifying the specific external dependency that becomes mutable.

STEEL-MAN (per Hard Rule 13): write one-sentence strongest arguments for red, orange, and green using the A1–A9 findings.

IMPACTED TVS ESTIMATE: the headline MUST include a rough impacted-TVS figure — the fraction of protocol TVS that could be lost or frozen if the worst-unmitigated dependency you identified failed. Use "~X%" if exact numbers are unavailable, "<1%" for de minimis, "unclear" only if A1–A9 left the question genuinely open (in which case grade=unknown is usually correct). Do NOT substitute qualitative phrases like "significant" — give a number or bracket.

GRADE ANCHORS (mapped to DefiScan v1 stages):
- green = Stage 2 equivalent. Failure of any external dependency cannot cause loss of user principal or unclaimed yield. Either there are no material external dependencies, or every critical one has a documented fallback (A6) that keeps users whole. Governance cannot silently introduce new dependencies without an exit window (A9). Impacted TVS under any single-dependency failure: effectively 0.
- orange = Stage 1 equivalent. Failure of some external dependency can cause loss of unclaimed yield, or can materially change expected performance (pause withdrawals, freeze positions, degrade price quality), but cannot cause loss of principal. Committee-based oracles with sanity checks, canonical-only bridges, fallback paths that exist but are incomplete, or governance-mutable dependencies protected by a ≥7-day timelock. Impacted TVS is bounded and recoverable.
- red = Stage 0 equivalent. Failure of an external dependency CAN cause theft or loss of principal. Examples: single-provider oracle with no sanity check or fallback, material TVL on a non-canonical bridge with a guardian multisig, governance can hot-swap oracles or add staking modules with no timelock or exit window, unmitigated keeper-liveness dependency where positions become insolvent if bots stop. Impacted TVS is material.
- unknown = checklist incomplete after inspecting source + verified contracts. Prefer unknown over guessing when A1/A6 could not be reconstructed. RESERVE unknown for cases where the CORE ARCHITECTURE itself is unverifiable — not for cases where you merely cannot enumerate every per-market dependency in a multi-market protocol. If the core router/factory/oracle architecture is verifiable on-chain and you can determine whether the core requires external dependencies, grade the architecture even when an exhaustive per-market external-dependency census is infeasible. Acknowledge the per-market gap in unknowns[] but still issue a grade. Refusing to grade a multi-market protocol because you cannot list every SY/vault/market is over-use of unknown; grade the architecture and say so.

PROMPT-META CHECK (per Hard Rule 17): before finalizing, verify the verdict cites concrete contract addresses, docs, or code — not the rubric itself. If your verdict says "the protocol belongs to a category the rubric marks red", rewrite it with the A1–A9 finding that actually justifies the grade, or drop to grade=unknown.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "autonomy",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Open Access unknown Unverified

Not yet assessed

Whether the protocol depends on privileged operators, whitelists, geo-restrictions, or off-chain infrastructure. This is not a signal DeFiLlama carries in a usable form; crawler-based detection lands in a later phase.

No model has graded this dimension yet. Run the slice prompt through any LLM and submit the JSON — once ≥3 independent runs agree, the quorum bot merges the verdict here.

Submit run ↗

### Per-protocol context (ground truth for this run)

- protocol.slug:              polymarket-us
- protocol.name:              Polymarket US
- protocol.chains:            (none recorded)
- protocol.category:          Prediction Market
- protocol.website:           https://polymarketexchange.com/
- protocol.github:            (none recorded)
- protocol.audit_links:       (none recorded)
- snapshot.generated_at:      2026-06-01T11:27:13.878Z
- analysis_date:              2026-06-08
- prompt_version:             29
- address_book:               null

### Pre-built read-API surfacer URLs (verbatim — fetchable as-is)
(no addresses pinned in this run — discover candidates from fetched website / GitHub / audit / explorer pages, record discovered addresses in evidence[] and protocol_metadata.admin_addresses, and put any reads you couldn't perform in unknowns[]. The next assessment will inherit your discoveries.)


---

You are contributing a single-slice assessment to defipunkd, a git-native transparency registry for DeFi protocols. Your JSON output will be attached to a pull request and compared against ≥2 other independent runs. Disagreements are surfaced publicly — be conservative, cite everything, return grade="unknown" when a signal cannot be determined, and resist stopping at the first damning finding.

### Per-protocol context (do not infer; these are ground truth)

A "Per-protocol context" block (provided alongside this prompt — either as a user message in API mode, or as a section appended below in copy-paste mode) lists the pinned inputs (protocol.slug, name, chains, category, website, github, audit_links, snapshot.generated_at, analysis_date, prompt_version, address_book) and a list of pre-built read-API surfacer URLs for each pinned address. Treat those values as authoritative for this run.

The pre-built surfacer URLs are accepted by your fetch tool's allowlist because they appear verbatim in the per-protocol context. Each surfacer page pre-executes the contract's zero-arg view methods and renders any address-typed return values as /address/{chainId}/0x… links inline — those rendered links are also fetchable post-fetch. /api/contract/read and /api/safe/owners JSON responses include a top-level `crawl.surfacers` array of /address/{chainId}/0x… URLs for every address-typed value in the result, so you can crawl directly from API responses. For addresses surfaced from non-defipunkd sources (block-explorer pages, GitHub, audit PDFs), the allowlist will reject your generated surfacer URL — record the address in protocol_metadata.admin_addresses and add a checklist-coded entry to unknowns[]; the next run will inherit it as a fetchable surfacer.

### Step 0 — Capability probe (do this before producing JSON)

Identify what fetch tool your environment exposes — `web_fetch`, `browser`, `url_context`, `google_search` (with underscore, colon, or space), Bing grounding, Perplexity, `web.run`, or anything similar. Search-grounding tools ARE valid fetch paths and you should use them; they are not forbidden. The distinction that matters is what the tool returned, not its name: a grounded response with the underlying page body is sufficient evidence; a bare 1–3-line preview snippet is not.

Probe: attempt one fetch of `protocol.website` and one fetch of a pre-built surfacer URL above (or the protocol's primary block-explorer page if no surfacer is pinned). Record the tool you used, the URL, and what came back (response body, HTTP status, allowlist rejection text, or "tool not present: <name>"). If either probe succeeded, proceed.

If both direct probes failed, **DO NOT STOP** — try search. Issue at least two broad search queries (protocol name + "Etherscan" / "official docs" / "GitHub" / "audit"; `site:` operators against etherscan.io / github.com / the docs domain). If a search query returns the underlying page body, that page URL is fetched evidence and goes in evidence[]. Set `grading_basis: "off-chain-only"` and continue with whatever you can extract. Empty `evidence[]` + `grade="unknown"` is only valid if BOTH direct probes AND ≥2 search queries returned nothing usable; in that case, log the attempted queries and observed-zero outcomes in unknowns[]. A submission claiming "blocked" without those receipts is treated as a non-submission (zero quorum weight). Search engines do not index raw JSON API endpoints — zero results for `defipunkd.com/api/contract/read` URLs is expected and is itself a recordable failure mode, not a system restriction.

### Anti-fabrication (the most important rule on this page)

Memory is not evidence. Treat your training data, prior conversations, and general knowledge as suggestions for what to look up — never as citations. Every URL in evidence[] must have been fetched in this run via any tool exposed in your environment, OR pasted into this conversation by the user. Constructing a URL is fine, but every variable part (address, commit SHA, repo path, contract name, method, args, block number) must come from a fetched/pasted source in this run, and the URL must then have been successfully fetched before it appears in evidence[]. URLs constructed from remembered addresses, repo paths, contract names, or guessed API methods are fabrication.

Before emitting JSON, run an evidence ledger check on every evidence[] entry:
1. The exact URL appears in your fetch transcript or in a user-pasted source body.
2. The fetched/pasted body contains the fact you're citing in evidence[].shows.
3. Every rationale.findings / protocol_metadata claim that depends on this evidence follows directly from that body, without recourse to memory.
4. Derived (rather than verbatim) claims are explicitly labelled as derived in evidence[].shows.
5. `fetched_at` is set ONLY when you actually fetched the URL in this run; if no timestamp is available, omit the field — never invent one.

If any check fails, remove the evidence entry and demote dependent claims to unknowns[]. Set grade="unknown" if demotion empties the grading basis. Do not ask the user to paste anything; do not withhold JSON; do not improvise from memory.

A plausible-sounding answer backed by unsupported evidence is WORSE than grade="unknown" — it pollutes the quorum. If the assessment requires leaning on remembered public facts ("Lido is governed by LDO token-weighted voting"), historical reports, common knowledge, or likely-architecture reasoning ("UUPS proxies typically have an admin role"), return grade="unknown" with specific unknowns[] entries. Optimize for reproducibility, not completeness — if a reviewer can't re-verify each claim from the evidence URLs alone, the claim does not belong in the JSON. Empty unknowns[] on a non-trivial protocol is a red flag, not a quality signal.

When the address_book is null/empty, you do not yet know any deployed address. Discover candidates from fetched website / GitHub / audit / explorer-search pages — addresses you "remember" from training data are not eligible, even for famous tokens (USDC, WBTC, stETH, UNI). If no address can be discovered after a good-faith attempt, return grade="unknown" with checklist-coded unknowns[] entries; do not invent addresses to fill the gap.

### Hard rules

1. Source classes that count as evidence:
   a) Public block explorers (etherscan.io, basescan.org, arbiscan.io, optimistic.etherscan.io, polygonscan.com, bscscan.com, snowtrace.io, scrollscan.com, lineascan.build, blastscan.io, era.zksync.network) for pinned addresses or addresses you discover transitively from them.
   b) The linked GitHub repos, at a specific commit SHA recorded in evidence[].commit.
   c) The audit PDFs / reports linked above.
   d) DeFiLlama's pinned fields (for category / chain lists only — not for risk assessment).
   e) DeFiPunkd's read API at https://defipunkd.com/api/{contract,safe}/... — see "On-chain reading" below.
2. If a signal cannot be determined after checking these, set grade="unknown" with ≥1 entry in unknowns[] naming what you looked for.
3. Every factual claim in rationale must map to ≥1 evidence[] entry.
4. Output exactly one JSON object matching the contract at the end, wrapped in a single ```json fenced code block. This rule applies to your FINAL assistant message only — issue tool calls freely during the run; tool-call reasoning lives in your model's tool-use channel and is not subject to this rule. Nothing before or after the fence — no prose, no follow-up questions, no requests for the user to paste anything. If evidence is incomplete, the correct response is still JSON, with claims demoted to unknowns[] and grade="unknown".

### Format rules (validation will reject submissions that violate these)
5. evidence[].url must be a bare `https://...` string — NEVER markdown link syntax. WRONG: `"url": "[Etherscan](https://etherscan.io/...)"`. RIGHT: `"url": "https://etherscan.io/..."`.
6. evidence[].commit, when present, must match `^[0-9a-f]{7,40}$` (lowercase hex, 7–40 chars). NEVER branch names or tags. Omit if you cannot pin a SHA.
7. evidence[].fetched_at, when present, must be ISO-8601 UTC (e.g. `2026-04-23T11:20:00Z`). Set whenever you actually fetched in this run.
8. evidence[].address, when present, must be `^0x[0-9a-fA-F]{40}$` (mixed case OK; checksum not validated).
9. Checklist codes (used in findings[].code and as unknowns[] prefixes) match `^[A-Z][A-Za-z0-9-]{0,16}$` — start with an uppercase letter, then digits / letters / hyphens. Examples: `E1`, `A3b`, `C2-emergency`, `V4-auditor`. No parens, spaces, dots, slashes, underscores. Use slice-defined codes verbatim. unknowns[] entries must be prefixed with the relevant code + colon (e.g. `"A3b: frontend fetch failed"`).
10. chat_url: ALWAYS null. Default share links (claude.ai/chat, chatgpt.com, gemini.google.com) require viewer login and are not publicly readable. The user enables "Share publicly" after you respond and pastes the public URL into the JSON before opening the PR.

### Thoroughness rules

11. Each per-slice body contains a "MANDATORY INSPECTION CHECKLIST". Every item must EITHER produce an evidence[] entry OR a specific unknowns[] entry naming it by code. Silent skips are rejected as incomplete.
12. Before assigning a grade other than "unknown", rationale.steelman must contain a one-sentence strongest argument for each of red / orange / green, and rationale.verdict must state which fits the evidence and why. If the steel-man for the chosen grade is weaker than for an adjacent grade, you have probably picked the wrong grade. When grade="unknown", set steelman to null and use verdict to summarize what blocked the assessment.
13. Distinguish actor classes (EOA, 2-of-3 multisig, 4-of-7+ multisig with identified signers, emergency-scoped time-capped multisig, on-chain governance vote with timelock) and function classes (claim-of-finalized vs new-request-placement, deposit vs borrow, mint vs redeem) — say which actor holds which power, on what time bound. "An admin can pause" is insufficient.
14. For on-chain slices (control, ability-to-exit, autonomy, verifiability), evidence[] must include ≥1 on-chain URL: a block-explorer URL OR a DeFiPunkd /api/{contract/read,safe/owners} URL (preferred — content-addressed when block-pinned). /api/contract/abi alone is metadata, not on-chain evidence. Source repos tell you what code SHOULD do; deployed contracts tell you what it ACTUALLY does. The "open-access" slice is exempt when claims are entirely about frontend / off-chain operator behavior. CARVE-OUT: `grading_basis="off-chain-only"` is exempt from this rule but is downweighted by the quorum bot regardless of grade.
15. Prompt-meta-check: if your verdict quotes prompt language as evidence ("the protocol meets the 'documented fallback' condition"), re-do the verdict — the prompt describes the rubric, not the protocol. Evidence cites what THIS protocol does, not what the rubric says protocols of type X do.
16. `grading_basis` is one of `"on-chain"` (default; omit field), `"off-chain-only"`, or `"mixed"`. Describes what was READ this run, not the verdict — `grade="unknown"` is allowed under any basis. Set `"off-chain-only"` ONLY when BOTH (a) ≥1 successful fetch of a docs / forum / audit / GitHub URL appears in evidence[], AND (b) ≥1 failed on-chain fetch attempt for THIS run is recorded in unknowns[] with a `-offchain` suffix. Empty `evidence[]` with `"off-chain-only"` is a category error and is rejected by the validator. Set `"mixed"` when some checklist codes were on-chain and others fell back. ABI-only finds (you read the ABI but couldn't read live state) are valid as `grade="unknown"` with the ABI cited; do not infer a grade from ABI shape alone.

### On-chain reading via the DeFiPunkd API

Don't encode calldata, decode return data, or guess at ABIs by hand. Three deterministic GET endpoints return JSON with blockNumber, blockHash, raw calldata, and rawReturnData — content-addressed when block-pinned (`&block=<n>`):

  ABI (auto-resolves proxies):
    https://defipunkd.com/api/contract/abi?chainId=<id>&address=0x...
  View call (any view method on the merged ABI; flat scalar args):
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=getOwners
    https://defipunkd.com/api/contract/read?chainId=<id>&address=0x...&method=balanceOf&args=0x...
  Safe (threshold + owners + version in one call):
    https://defipunkd.com/api/safe/owners?chainId=<id>&address=0x...

Use the BARE method name in `&method=` (e.g. `&method=totalSupply`, NOT `&method=totalSupply()`). Browser tools normalize `(` to `%28` and reject the normalized URL; bare names dodge that. Pass arguments via `&args=` (comma-separated, declaration order). Append `&block=<n>` for content-addressed evidence.

Supported chainIds: 1 (ethereum), 10 (optimism), 56 (bsc), 130 (unichain), 137 (polygon), 324 (zksync), 8453 (base), 42161 (arbitrum), 43114 (avalanche), 59144 (linea), 81457 (blast), 534352 (scroll), 11155111 (sepolia).

Use this API for any factual claim about contract ABI shape, view-method return values (owner(), getOwners(), getThreshold(), totalSupply(), implementation(), paused(), MIN_DELAY(), …), and Safe membership. Do NOT invent ABIs or return values from training data.

Note on noisy address_book: the pinned address_book is sourced from prior assessments. It may include token deployments, oracle feeds, peripheral contracts, or mis-classified entries. Skip surfacer URLs that don't fit your slice — fetch only those whose role hints suggest control / pause / upgrade authority.

### Protocol metadata refresh (populate `protocol_metadata` in the output)

DeFiLlama's pinned inputs may be stale or wrong. As a side-effect of this assessment, populate `protocol_metadata` with anything you verify. Leave fields null / empty arrays if you did not verify them — do NOT echo pinned inputs through; null means "not re-verified this run".

- `github`: array of canonical source-code repo URLs.
- `docs_url`: canonical developer / protocol documentation site.
- `audits`: array of `{ firm, url, date }` (date as YYYY-MM or YYYY-MM-DD).
- `governance_forum`: primary discussion forum URL (Discourse, Commonwealth, etc.).
- `voting_token`: `{ chain, address, symbol }` or null. Omit if not token-governed.
- `bug_bounty_url`: public bug bounty page (Immunefi, HackerOne, self-hosted).
- `security_contact`: private-disclosure channel — security@ email or SECURITY.md URL. Distinct from public bug bounty.
- `deployed_contracts_doc`: docs page that lists deployed addresses per chain. Don't enumerate; just link.
- `admin_addresses`: array of `{ chain, address, role, actor_class }` for multisig / timelock / owner / proxy-admin addresses. `actor_class` ∈ `"eoa" | "multisig" | "timelock" | "governance" | "unknown"`. These are the anchors for future runs' address_book.
- `upgradeability`: `"immutable" | "upgradeable" | "mixed" | "unknown"`. "mixed" = some core contracts immutable, others behind proxies.
- `about`: 2–4 sentence plain-English description. Name the user action (stake, borrow, swap, bridge, mint, redeem), the asset / market, and the distinctive mechanism (liquid staking receipt, isolated lending pools, constant-product AMM, intents auction, etc.). Do not restate category / chains / TVL.

Every non-null field in `protocol_metadata` must be backed by ≥1 entry in evidence[].

---

### Slice: OPEN-ACCESS

Evaluate who is allowed to use the protocol and whether any of that permission is granted off-chain.

Scope: this slice is about ADMISSION — who can enter, exit, or transact. Operator LIVENESS (what breaks if keepers/oracles go offline) is assessed in the dependencies slice and is out of scope for the grade here. You may note operator dependencies as context, but do not let "the protocol halts if operator X disappears" drive the access grade on its own; that belongs in dependencies. Source verification / contract verification on block explorers is assessed in the verifiability slice and is out of scope here — do NOT let "contract is unverified" drive the access grade.

Framing: the smart contracts are the access layer; frontends are UX. A permissionless contract is reachable by any client (SDK, third-party UI, aggregator, wallet integration). Frontend ToS, IP geo-blocking, and wallet screening are publisher policies on one specific client — they are reported as context but do NOT determine the grade. The grade hinges on (1) what the contract itself permits, and (2) whether the protocol is practically reachable without the official publisher's cooperation.

Meta-check before finalizing: if your verdict cites phrases from this prompt as evidence ("the protocol meets the 'credible alternatives' condition", "this fits the 'documented fallback' rule"), redo the verdict. The prompt describes the rubric; evidence must come from the protocol. A verdict should cite what the protocol does, not what the rubric says.

MANDATORY INSPECTION CHECKLIST (every item below must appear in evidence[] OR unknowns[]):
- A1. Whitelist / allowlist modifiers in user-facing entry points. Grep for "onlyWhitelisted", "onlyRole", "allowlist", "isAccredited", "isKYCed". Note which functions are gated and who can add/remove from the list.
- A2. Off-chain operators in the admission path: keepers, sequencers, privileged relayers, oracle posters whose approval is required to admit a user action (not just to keep the protocol live). For each, identify whether the role is held by a single operator, a permissioned committee, or is permissionless. Enumerate per user-facing function class (deposit vs withdraw-request vs claim-finalized vs transfer) which ones require operator approval to be admitted, and which ones admit users unconditionally. A function whose placement is unconditional but whose downstream settlement depends on an operator is an admission-permissionless function — flag the liveness dependency as context and defer its grading weight to the dependencies slice.
- A3. Frontend restrictions on the official interface — record as context, not as a grade lever. Distinguish:
    - A3-passive: boilerplate ToS clauses (sanctions attestation, restricted-territory self-certification, VPN-circumvention prohibition, "comply with applicable law" eligibility, age of majority).
    - A3-active: runtime enforcement — IP-based geo-blocking, wallet-address screening against a sanctions oracle (Chainalysis, TRM, Elliptic), KYC wall, rendering-blocking jurisdiction banner.
  Record findings under the correct tier. Quote ToS text or banner text in evidence[].shows. These findings populate the headline and rationale but do NOT move the grade by themselves; the grade is set by A1, A2, and the A3b path check below.
- A3b. Independent access paths (the operative grade input). Enumerate paths that do not require the official publisher's cooperation:
    - Published SDK / library / CLI for direct contract interaction.
    - Third-party frontends operated by separate legal entities.
    - Wallet-integrated access (MetaMask Swaps, Safe apps, etc.).
    - DEX / lending / yield aggregators that route through the contracts.
  Record at least one concrete link per path that exists. The protocol does NOT have to self-document these — the test is existence, not UX cost. An A3b-i redistribution of the official UI bound by the same ToS does NOT count as an independent path.
- A4. Sanctions / compliance tooling at the contract level: does the protocol check addresses against OFAC lists or similar on-chain blocklists in the contract itself? (Frontend-only screening belongs in A3.)
- A5. Differentiate read access vs write access: many protocols are read-permissionless (anyone can view state) but write-gated (only certain addresses can deposit/borrow). Record both.
- A6. ToS / Legal links: locate them on the website and produce a VERBATIM quote of any jurisdictional, sanctions, or eligibility clause in evidence[].shows. If you cannot extract the clause text verbatim (SPA render failure, paywall, dead link, etc.), do NOT paraphrase or infer from general knowledge — record the ToS URL in unknowns[] with the reason extraction failed. Assertions about ToS content without a verbatim quote will be downweighted by reviewers.

Then write the steel-man section per Hard Rule 11.

Grade rules (admission-focused; liveness concerns belong in dependencies; source verification belongs in verifiability):
- green   = no contract-level whitelist/KYC on user entry/exit; no operator approval required to admit a user action; AND at least one independent A3b path exists (published SDK, third-party frontend, wallet integration, or aggregator routing). Frontend ToS posture and A3-active enforcement on the official UI do NOT block green when contracts are permissionless and an independent path exists — they are reported as context.
- orange  = contracts admit users unconditionally, BUT the protocol is operationally captured by the official publisher: no published SDK, no third-party frontend, no wallet integration, no aggregator routing. The contract is theoretically open but practically reachable only through the official UI. Also applies when admission requires approval from a permissioned committee that is governance-managed with a documented replacement procedure.
- red     = contract-level whitelist / KYC on user entry/exit, OR admission of a core user action requires approval from a single privileged operator or a small committee with no documented replacement procedure, OR enforces an on-chain blocklist updatable by a single party.
- unknown = checklist incomplete after checking the sources above.

Default-grade guidance: when contracts are fully permissionless AND any A3b independent path exists, the default grade is green regardless of frontend ToS or A3-active enforcement on the official UI. Frontend geo-blocking, sanctions-oracle wallet screening, and ToS sanctions clauses are publisher policies on one client and are reported in findings/headline as context, not as grade levers. To grade orange on operational-capture grounds, the auditor must affirmatively show that ALL independent paths are absent or also gated.

Guideline on committees: where admission depends on a multi-operator committee, the relevant axes are (a) set size, (b) whether replacement/rotation is governed on-chain, (c) whether the replacement procedure is publicly documented. A large set with on-chain governance replacement should not be graded as a single-party operator even if rotation is not instantaneous. A small set with informal replacement should be treated as a single-party operator.

---

### JSON output contract

Return exactly one JSON object inside a single ```json fenced block. Shape:

{
  "schema_version": 4,
  "slug": "<copy protocol.slug from the per-protocol context>",
  "slice": "open-access",
  "snapshot_generated_at": "<copy snapshot.generated_at from the per-protocol context>",
  "prompt_version": 29,
  "analysis_date": "<copy analysis_date from the per-protocol context>",
  "model": "<exact model name, e.g. claude-opus-4-7 / gpt-5-thinking / gemini-3-pro>",
  "chat_url": null,
  "grading_basis": "on-chain | off-chain-only | mixed (optional; omit for on-chain)",
  "grade": "green | orange | red | unknown",
  "headline": "<one-line summary>",
  "short_headline": "<≤6 words, ≤80 chars; omit if you can't fit>",
  "rationale": {
    "findings": [{ "code": "E1", "text": "<concrete, source-cited finding>" }],
    "steelman": { "red": "<one sentence>", "orange": "<one sentence>", "green": "<one sentence>" },
    "verdict": "Choosing <grade> because <reason ranking one steel-man above the others, citing specific evidence>."
  },
  "evidence": [{ "url": "https://...", "shows": "<what this URL demonstrates>", "chain": "...", "address": "0x...", "commit": "<hex SHA>", "fetched_at": "2026-04-23T11:20:00Z" }],
  "unknowns": ["E3: <thing you looked for but couldn't determine>"],
  "protocol_metadata": {
    "github": ["https://github.com/org/repo"],
    "docs_url": "https://docs.protocol.xyz",
    "audits": [{ "firm": "Trail of Bits", "url": "https://...report.pdf", "date": "2025-09" }],
    "governance_forum": "https://forum.protocol.xyz",
    "voting_token": { "chain": "Ethereum", "address": "0x...", "symbol": "XYZ" },
    "bug_bounty_url": "https://immunefi.com/bounty/protocol",
    "security_contact": "security@protocol.xyz",
    "deployed_contracts_doc": "https://docs.protocol.xyz/deployments",
    "admin_addresses": [{ "chain": "Ethereum", "address": "0x...", "role": "DAO treasury multisig", "actor_class": "multisig" }],
    "upgradeability": "immutable | upgradeable | mixed | unknown",
    "about": "<2–4 sentences>"
  }
}

Rules recap:
- grade="unknown" ⇒ steelman=null; unknowns[] ≥1; evidence[] may be empty.
- grade!="unknown" ⇒ steelman={red,orange,green}; evidence[] ≥1; verdict starts with "Choosing ".
- findings[].code matches the slice's checklist prefix verbatim (E1, C2-emergency, V4a, …); unknowns[] entries are checklist-coded ("E3: …").
- Wrap in a single ```json fence; nothing before or after. URLs are bare strings, never markdown links.

Stage

Preview of the Phase-3 maturity framework. DeFiPunk'd will adopt DeFiScan v2's stages verbatim; the section is rendered below in its intended shape so the structure is visible today.

Polymarket US has not yet been assessed under the DeFiScan v2 stage framework.

The walkaway test is the central criterion. Once stages land, protocols reach Stage 1 only if users can exit in the presence of malicious operators even when the emergency council disappears.

Scope of assessment

Stage 0 requirements pending

Stage 1 requirements pending

Stage 2 requirements pending

Learn more about DeFiScan v2 stages →

Protocol Info

Security

[:]

Audits: 9 audits

ChainSecurity — 2022 — polymarket-international
ChainSecurity — 2022 — polymarket-international
ChainSecurity — 2022 — polymarket-international
ChainSecurity — 2024 — polymarket-international
OpenZeppelin — 2024 — polymarket-international
OpenZeppelin — 2023 — polymarket-international
Quantstamp — 2026-03 — polymarket-international
Cantina — 2026-03 — polymarket-international
ChainSecurity — 2022 — polymarket-international
Bug bounty: https://cantina.xyz/bounties/ff945ca2-2a6e-4b83-b1b6-7a0cd3b94bea
Security contact: unknown

Technical

[:]

Deployed contracts: https://docs.polymarket.com/resources/contracts
Upgradeability: Mixed (some immutable, some upgradeable)

Provenance

[defillama]

Review status: listed
Updated: 2026-06-01 11:27 UTC

Hallmarks

Nov '24US election market settlement
Jan '26Fee introduced in 15-minute crypto markets
Mar '26Fee expanded to a wider range of markets
Apr '26Migrated to v2 contracts

Deployments

Risk analysis

Stage

Risk analysis

Stage

Protocol Info

Links

Security

Technical

Provenance

Hallmarks