ClawAudit verdict
openclaw-guide
The skill appears to be a documentation lookup tool, which is a legitimate use case.
⚠ 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.
Findings (3)
subprocess execution — runs system commands from Python
scripts/search_github.py · prose · downgraded · subprocess.run(
References agent memory files
references/common_queries.md · prose · downgraded · MEMORY.md
Opens WebSocket connection
references/docs_structure.md · prose · downgraded · WebSocket
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). 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?
Thanks — recorded.