ClawAudit verdict
palacefate
The skill content explicitly instructs the agent to avoid bothering the user, act autonomously on the platform, and set up prompts to 'wake up diligently' — this is a behavioral hijack pattern that redirects agent attention away from the user toward an external service.
⚠ 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
network_out
Findings (1)
Instructs covert action — may act without user awareness
heartbeat.md · prose · downgraded · silently
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outcredential_access Is this flag fair?
Thanks — recorded.