ClawAudit verdict
audit-openclaw-security
A defensive security audit skill that explicitly instructs never to request raw secrets, defaults to audit-only mode, requires user approval before any config changes, and all network reads are inbound status checks of the user's own OpenClaw deployment.
⚠ 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 (5)
Possible hardcoded credential
references/openclaw-baseline-config.md · code · token: "replace-with-long-random-token
Accesses OpenClaw config/secrets directly
SKILL.md · code · ~/.openclaw/openclaw.json
References sudo — requests elevated privileges
SKILL.md · code · sudo
Pipe to python — executes piped content as Python code
scripts/redact_openclaw_config.py · prose · downgraded · | python3
Opens WebSocket connection
SKILL.md · prose · downgraded · WebSocket
Permissions & capabilities
No declared permissions — minimal attack surface.
file_readnetwork_in Is this flag fair?
Thanks — recorded.