ClawAudit verdict
swarm-coding-skill
The skill generates complete projects with code, tests, and CI. While powerful, it seems to be designed for legitimate software development purposes.
⚠ 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)
<script> tag in markdown — potential code injection
orchestrator.js · prose · downgraded · <script>
Uses exec() — may execute shell commands
orchestrator.js · prose · downgraded · exec(
Node http/https module — low-level network access
orchestrator.js · prose · downgraded · require('https')
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.