ClawAudit verdict

k-deep-research

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

The skill performs systematic deep research without exfiltrating or executing malicious code.

⚠ 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.

78
security
100
transparency
90
maintenance

Findings (3)

Pattern match medium

References agent memory files

references/autonomy-patterns.md · code · MEMORY.md

Pattern match medium

Accesses .ssh directory

references/openclaw-architecture.md · prose · downgraded · .ssh/

Pattern match low

Opens WebSocket connection

references/openclaw-architecture.md · prose · downgraded · WebSocket

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