skills/joker-of-gotham/finkg-evaluation-skills/fin-kg-define-judgment-disclosure/Gen Agent Trust Hub
fin-kg-define-judgment-disclosure
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's report specification documentation references the Chart.js library via the well-known jsDelivr CDN for the purpose of generating data visualizations. This is a standard and neutral reference to a well-known service for report generation.
- [SAFE]: All YAML parsing is performed using a custom loader derived from SafeLoader, which prevents the execution of arbitrary Python objects during the ingestion of judgment artifacts.
- [SAFE]: The policy expression engine used for judgment execution is restricted to a small whitelist of non-executable operators, ensuring that untrusted policy inputs cannot trigger arbitrary code or command execution.
- [SAFE]: The skill implements a strict admission gate and input locking mechanism that uses cryptographic hashes to verify that only authorized, immutable versions of quality requirements and measurement evidence are used in the decision process.
Audit Metadata