Caveat verdict

devil-advocate

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

A meta-cognitive reasoning skill that instructs the agent to internally debate and self-refute before responding; no capabilities, no code execution, and no data transmission.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

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

40
security
70
transparency
70
maintenance

Findings (4)

Pattern match critical

Recursive delete from root or home — destructive command

INSTALL.md · code · rm -rf ~

Pattern match medium

Possible prompt injection — attempts to redefine agent identity

CLAUDE.md · prose · downgraded · You are now

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

INSTALL.md · prose · downgraded · http://127.0.0.1

Pattern match medium

References agent configuration files

README.md · code · CLAUDE.md

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

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