ClawAudit verdict
mcp-integration
openclaw-mcp-plugin
Integration guide for discovering and executing tools from MCP servers configured by the user; behavior matches stated purpose of accessing user-configured external tools and data sources.
⚠ 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 (5)
Possible hardcoded credential
docs/CONFIGURATION.md · code · API_KEY="your-api-key-here
Accesses OpenClaw config/secrets directly
docs/CONFIGURATION.md · code · ~/.openclaw/openclaw.json
Accesses shell history/config
docs/CONFIGURATION.md · code · ~/.zshrc
References sudo — requests elevated privileges
docs/TROUBLESHOOTING.md · code · sudo
Uses spawn() — can execute external programs
config/openclaw.plugin.json · prose · downgraded · spawn (
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_in Is this flag fair?
Thanks — recorded.