scenario-model-comparison

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: Evaluated the skill's processing of model-generated assets. The workflow uses pre-defined criteria and specialized evaluation tools (such as asset_analyze), which is consistent with its primary purpose and maintains a safe processing environment.
  • [EXTERNAL_DOWNLOADS]: Reviewed the instructions for installing sibling skills via npx. These references point to official vendor resources (scenario-labs/skills) and involve user-initiated commands, posing no risk to the autonomous execution environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 03:12 PM
Security Audit — agent-trust-hub — scenario-model-comparison