Caveat verdict
agenttax
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
Reads a credential and makes network calls to a legitimate tax API as described; no malicious behavior.
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.
95
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 environment variable. (1 sensitive: AGENTTAX_API_KEY). Requires 1 system binary. (1 elevated: curl).
network_outcredential_access Was this verdict right?
Thanks — recorded.