israeli-ai-compliance-kit
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a regulatory resource providing templates and informational guidance. All scripts operate locally on provided input files without performing network operations, credential harvesting, or unauthorized file system modifications.
- [INDIRECT_PROMPT_INJECTION]: The skill provides an ingestion surface for external data used to generate compliance artifacts. 1. Ingestion points: The scripts
scripts/generate_model_card.pyandscripts/classify_eu_ai_act_risk.pyaccept JSON data via the--inputparameter. 2. Boundary markers: The scripts utilize structured JSON parsing to separate input data from execution logic. 3. Capability inventory: Capabilities are restricted to local text rendering and console output; the code does not utilizesubprocess,eval(), or other dynamic execution vectors. 4. Sanitization: Inputs are handled using standard JSON loading libraries and validated against expected schemas. This surface is necessary for the skill's utility and follows secure processing practices.
Audit Metadata