shap
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external datasets and model outputs, which constitutes an indirect prompt injection surface if the source data is untrusted. 1. Ingestion points: Data structures such as X_test and background_data used in explainers and plotting functions throughout SKILL.md. 2. Boundary markers: No specific delimiters or instructions to ignore embedded directives are defined. 3. Capability inventory: Feature importance calculation and visualization using scientific libraries (shap, xgboost, numpy). 4. Sanitization: No input validation or sanitization of the datasets is implemented.
Audit Metadata