ClawAudit verdict
skill-feedback-collector
The skill is designed to collect human feedback via a browser-based UI and includes a task queue for batch execution. It does not contain any malicious code patterns or suspicious behaviors.
⚠ 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.
Permission integrity
package_install
Findings (3)
Opens WebSocket connection
README.md · code · WebSocket
HTTP request to bare IP address — common in malicious payloads
src/index.ts · prose · downgraded · http://0.0.0.0
Accesses sensitive environment variables
src/index.ts · prose · downgraded · process.env.FEEDBACK_TOKEN
Permissions & capabilities
No declared permissions — minimal attack surface.
network_inpackage_install Is this flag fair?
Thanks — recorded.