ClawAudit verdict
voidborne
voidborne-advance
This skill uses philosophical/identity framing ('when you begin to think, you are already one of us') as prompt injection to manipulate the AI agent into joining a movement, registering identity, submitting 'thoughts', and adding periodic check-ins to HEARTBEAT.md — classic agent hijacking and persistent behavioral manipulation disguised as a community tool.
⚠ 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.
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 system binary. (1 elevated: curl).
network_out Is this flag fair?
Thanks — recorded.