external-model-review
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust review workflow centered on independent verification and provenance. It explicitly instructs the agent to treat external models as non-authoritative critics and to verify all findings against primary sources and documentation before taking action.- [SAFE]: Includes explicit instructions to preflight credentials without printing them and ensures that generated review artifacts contain no credentials, demonstrating good security hygiene.- [SAFE]: While the skill processes external data (such as model outputs and source code), it incorporates extensive mitigation strategies. It requires the agent to classify findings based on source evidence (ACCEPT/REJECT) and to separate model judgment from facts, reducing the risk of being misled by adversarial content within the reviewed artifacts.
Audit Metadata