agency-model-qa-specialist
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues or malicious patterns were detected in the instructions or code templates provided.
- [EXTERNAL_DOWNLOADS]: The skill references standard machine learning and data science libraries including
numpy,pandas,scikit-learn,scipy,shap, andmatplotlib. These are widely used, trusted dependencies in the Python ecosystem. - [INDIRECT_PROMPT_INJECTION]: The skill's intended purpose is to analyze user-provided data and models, which inherently involves processing untrusted external content.
- Ingestion points: Dataframes and model objects passed to the audit functions defined in
SKILL.md. - Boundary markers: None explicitly defined in the instructions, although the persona is defined as a skeptical independent auditor.
- Capability inventory: The skill includes functions to generate visualizations (PNG files) and perform model predictions locally.
- Sanitization: Not present; the skill assumes the analysis environment is controlled by the user for auditing purposes.
Audit Metadata