Caveat verdict
agent-ledger
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
The skill reads/writes local JSONL files and never sends data off‑machine or accesses secrets beyond a user‑provided wallet address stored locally.
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
90
transparency
70
maintenance
No red flags detected in static analysis.
Checked: 115 threat patterns · AST capability extraction · cross-zone compound shapes · permission integrity.
Permissions & capabilities
Requires 2 system binaries.
Was this verdict right?
Thanks — recorded.