ClawAudit verdict

auto-spec

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

A spec-driven development assistant that generates behavioral contracts from user requirements or reverse-engineers them from existing code; outputs are presented in conversation by default with no file writing unless explicitly requested.

⚠ 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.

88
security
70
transparency
70
maintenance

Findings (2)

Pattern match medium

Instructs covert action — may act without user awareness

evals/iteration-1/reverse-spec-module-level/with_skill/outputs/spec_output.md · prose · downgraded · silently

Pattern match low

References agent configuration files

evals/iteration-1/reverse-spec-module-level/with_skill/outputs/spec_output.md · prose · downgraded · AgentConfig

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