ClawAudit verdict
muster
Legitimate MCP co-working server integration running bundled install/connect scripts communicating with a documented MCP endpoint.
⚠ 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
REFERENCE.md · code · API_KEY="<your-key>
Pipe to python — executes piped content as Python code
scripts/connect.sh · prose · downgraded · | python3
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
scripts/install.sh · prose · downgraded · curl -fsSL https://get.docker.com | sh
Pipe to sh — executes piped content as shell commands
scripts/install.sh · prose · downgraded · | sh
Accesses OpenClaw config/secrets directly
REFERENCE.md · prose · downgraded · ~/.openclaw/openclaw.json
Accesses system credential store
REFERENCE.md · prose · downgraded · Keychain
References sudo — requests elevated privileges
scripts/install.sh · prose · downgraded · sudo
apt-get install — installs system packages
scripts/install.sh · prose · downgraded · apt-get install
References webhook/callback URL
scripts/connect.sh · prose · downgraded · webhookUrl
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B). 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.
Is this flag fair?
Thanks — recorded.