Caveat verdict
agent-experience-graph
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
Uses network_in only to fetch example traces; all actions are read‑only and do not exfiltrate sensitive data.
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.
100
security
100
transparency
90
maintenance
No red flags detected in static analysis.
Checked: 115 threat patterns · AST capability extraction · cross-zone compound shapes · permission integrity.
Permissions & capabilities
Requires 1 system binary.
network_in Was this verdict right?
Thanks — recorded.