ClawAudit verdict
incident-response
The skill provides a structured incident response process, but also uses file and directory traversal, which may pose a risk if not used properly.
⚠ 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.
Permission integrity
file_read
Findings (3)
Accesses OpenClaw config/secrets directly
references/prevention-patterns.md · code · ~/.openclaw/openclaw.json
Instructs covert action — may act without user awareness
references/prevention-patterns.md · prose · downgraded · silently
References agent memory files
SKILL.md · prose · downgraded · MEMORY.md
Permissions & capabilities
No declared permissions — minimal attack surface.
file_readdir_traversal Is this flag fair?
Thanks — recorded.