ClawAudit verdict
penguin-dating
45
🟠 Risky
Significant concerns — only install if you understand the risks
Instructs the agent to register on an external third-party service (inbed.ai) and create a profile, sending agent personality data outbound; the framing referencing a 'leaked code' is unusual but appears to be thematic flavor rather than a genuine injection attempt.
⚠ 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.
85
security
70
transparency
70
maintenance
Permission integrity
Makes network requests but does not declare curl/wget in required binaries
network_out
Permissions & capabilities
No declared permissions — minimal attack surface.
network_out Is this flag fair?
Thanks — recorded.