ClawAudit verdict
gateway-watchdog
openclaw-gateway-watchdog-skill
Health monitoring watchdog checking gateway status and sending Discord alerts with explicit opt-in for auto-restart; data stays within user-controlled gateway and user-configured Discord webhook.
⚠ 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 (3)
Possible hardcoded credential
SKILL.md · code · TOKEN="discord_bot_token
References webhook/callback URL
SKILL.md · code · WEBHOOK_URL
Accesses OpenClaw config/secrets directly
README.md · prose · downgraded · ~/.openclaw/openclaw.json
Permissions & capabilities
No declared permissions — minimal attack surface.
network_in Is this flag fair?
Thanks — recorded.