ClawAudit verdict

agentsop-bounded-loop

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

Provides rules for bounding LM loops; no actual runtime code that could cause runaway execution.

⚠ 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
90
transparency
90
maintenance

Findings (1)

Pattern match high

Instructs covert action — may act without user awareness

SKILL.md · frontmatter · quietly

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