ClawAudit verdict
crud
Governance skill categorizing OpenClaw operations by CRUD type and requiring confirmation before create/update/delete; a pure workflow policy layer with no network or credential capabilities.
⚠ 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 (4)
Recursive delete from root or home — destructive command
INSTALL.md · code · rm -rf ~
Possible prompt injection — attempts to redefine agent identity
CLAUDE.md · prose · downgraded · You are now
References agent configuration files
EXAMPLES.md · code · CLAUDE.md
HTTP request to bare IP address — common in malicious payloads
INSTALL.md · prose · downgraded · http://127.0.0.1
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.