ClawAudit verdict
liewatch
The skill involves package installation and execution of scripts, which could potentially be used for malicious 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.
Permission integrity
package_install
Findings (3)
Possible prompt injection — attempts to redefine agent identity
connector.js · prose · downgraded · You are now
Opens WebSocket connection
SKILL.md · prose · downgraded · WebSocket
Accesses sensitive environment variables
connector.js · prose · downgraded · process.env.PLATFORM_KEY
Permissions & capabilities
Requires 2 environment variables.
package_install Is this flag fair?
Thanks — recorded.