Caveat verdict
agent-estimation
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
Estimates task effort using internal round counts; no external side‑effects.
⚠ 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.
98
security
90
transparency
70
maintenance
Findings (1)
Pattern match low
Opens WebSocket connection
calibration-examples.md · prose · downgraded · WebSocket
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.