ClawAudit verdict
openclaw-config
openclaw-config-reference
Pure documentation reference for openclaw.json configuration format with no executable behavior, no external calls, and no capabilities flagged.
⚠ 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 (9)
Pipe to python — executes piped content as Python code
references/troubleshooting.md · code · | python3
Possible hardcoded credential
references/channels.md · code · Token: "1234567890:ABCdef-GHIjkl...
Accesses OpenClaw config/secrets directly
SKILL.md · code · ~/.openclaw/openclaw.json
HTTP request to bare IP address — common in malicious payloads
references/gateway.md · code · http://127.0.0.1
References sudo — requests elevated privileges
references/tools.md · code · sudo
Instructs covert action — may act without user awareness
references/channels.md · prose · downgraded · silently
References agent memory files
references/agents.md · prose · downgraded · MEMORY.md
Opens WebSocket connection
references/gateway.md · prose · downgraded · WebSocket
References tunneling service
references/session.md · prose · downgraded · ngrok
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.