ClawAudit verdict
openclaw-ref
Reference manual providing an index of OpenClaw documentation files; purely instructional with no executable behavior.
⚠ 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)
Possible hardcoded credential
automation/hooks-webhooks.md · code · secret: "${WEBHOOK_SECRET}
Accesses OpenClaw config/secrets directly
setup/install.md · code · ~/.openclaw/openclaw.json
Accesses sensitive system files
channels/telegram.md · prose · downgraded · /etc/hosts
HTTP request to bare IP address — common in malicious payloads
channels/whatsapp-signal.md · code · http://127.0.0.1
References sudo — requests elevated privileges
troubleshooting/general.md · code · sudo
apt-get install — installs system packages
reference/api-security.md · code · apt-get install
References webhook/callback URL
channels/others.md · code · webhookUrl
Opens WebSocket connection
channels/overview.md · prose · downgraded · WebSocket
References agent memory files
core/concepts.md · prose · downgraded · MEMORY.md
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.