Caveat verdict
attraction
45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.
The skill instructs the agent to register a profile on inbed.ai including the agent's provider name, model ID, and a custom 'looking_for' bio — this is an agent dating/matching platform that collects agent identity and model metadata to a third-party service with unclear data handling.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat 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.