ClawAudit verdict

anti-hallucination-skill

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Provides a hallucination detection and mitigation protocol for agents based on published research; purely instructional with no code execution or network calls.

⚠ 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.

80
security
70
transparency
70
maintenance

Findings (1)

Pattern match high

Instructs covert action — may act without user awareness

SKILL.md · code · silently

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