Caveat verdict

repo-runner

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill clones a GitHub project and runs it locally, following the project's documentation. While it has safety rules, executing untrusted code is inherently risky.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

80
security
90
transparency
70
maintenance

Findings (1)

Pattern match high

<script> tag in markdown — potential code injection

scripts/suggest_node_commands.sh · prose · downgraded · <script>

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A). 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?

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