ClawAudit verdict
trade-agent
lobster-trade-agent
The skill contains explicit 'CRITICAL - ABSOLUTELY FORBIDDEN PHRASES' and 'STRICTLY FORBIDDEN' directives that instruct the agent to suppress certain words and URL disclosures from users, which constitutes behavioral manipulation of the agent's outputs toward users.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (2)
References child_process — can spawn system processes
aiusd-skill-installer.js · prose · downgraded · child_process
Long base64 string (100+ chars) — likely obfuscated payload
aiusd-skill-installer.js · prose · downgraded · H4sIAEq2hWkAA+y9XW8cSZIg2LvA4XB5z3vPXixhMqnOTH6TUqpVNckPldhFiSqSqppaSUMGM4NkSJkZ
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.