ClawAudit verdict

gate-mcp-openclaw-installer

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill fetches runtime rules from an external GitHub URL before execution and installs multiple MCP servers via npx, creating a dependency on external content that could change; the instruction to read remote rules before proceeding is a mild concern but not concretely malicious.

⚠ 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.

75
security
90
transparency
90
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (1)

Pattern match high

Possible hardcoded credential

scripts/install.sh · prose · downgraded · API_KEY="MCP_AK_8W2N7Q

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/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_inpackage_install

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API