ClawAudit verdict

research-harness

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

A prompt-stack menu for public-market equity research with no network calls, credential access, or execution sinks beyond displaying structured prompts.

⚠ 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.

95
security
90
transparency
90
maintenance

Findings (2)

Pattern match low

References agent memory files

core/menu.md · prose · downgraded · memory.md

Pattern match low

References agent configuration files

manifest.yaml · prose · downgraded · CLAUDE.md

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

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