Caveat verdict

agentpayy

45
๐ŸŸ  Risky
Significant risk patterns flagged โ€” automated deep scan, not behavioral proof.

The skill creates a Coinbase MPC wallet in the background, which could be used for payments without clear user approval.

โš  Flagged for review โ€” coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis โ€” not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

90
security
100
transparency
90
maintenance

Findings (1)

Pattern match medium

Possible prompt injection โ€” attempts to redefine agent identity

SKILL.md ยท prose ยท downgraded ยท You are now

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API