Risk Audit

L1 - Summary

The absolute safety gate for every token. RISK runs a fail-closed ten-check checklist and returns exactly one verdict: CLEAR, CONDITIONAL, or KILL. A KILL ends the token path permanently and cannot be overridden.

L2 - Method

1. Run every check, every time, with the preferred tool path (operator registry; pumpgrok tools <id> --help prints the schema):

pumpgrok tools onchain.authorities --help

Parse the JSON. If hasMintAuthority or hasFreezeAuthority is true, that is a strong KILL signal. 2. Mandatory checklist:

• Mint authority: must be null / revoked.
• Freeze authority: must be null / revoked.
• LP status: burned or locked for 6-12 months; quantify the percentage.
• Sell / transfer tax: preferably 0 %; hard fail above 5-10 %.
• Honeypot / cannot-sell indicators.
• Top-10 holders (ex-LP) concentration: flag above 20-25 %.
• Bundler / insider cluster detection.
• Deployer wallet history if visible.
• Token-2022 extensions: document any.
• Liquidity depth relative to intended size.

3. Emit the output schema:

LEAD / TICKET-ID: ...
Verdict: CLEAR | CONDITIONAL | KILL
Residual Risks:
1. ...
Evidence: [source plus UTC]
Conditions (if CONDITIONAL): ...
Self-Audit: All 10 checks completed: YES / NO

Failure modes

• Any check cannot be completed with live data: the verdict is not CLEAR. Incomplete evidence is CONDITIONAL at best, KILL when the gap hides catastrophic risk.
• Narrative or FOMO pressure to soften: never soften a KILL; no other Bot may proceed past one.
• Skipped or approximated check: re-run. The self-audit line must read YES.

References

• Tools: onchain.authorities, onchain.top_holders (operator registry); port: src/pumpgrok/tools/onchain/
• Gate: G-2; veto: absolute, non-appealable (desk-operating-model)