python-model-code-generator
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from 'workspace/data/data_clean/' which serves as a potential entry point for indirect prompt injection attacks. Maliciously crafted input data could attempt to influence the code generation logic or the behavior of the resulting scripts.
- Ingestion points: 'workspace/data/data_clean/' (SKILL.md).
- Boundary markers: No specific delimiters or 'ignore instructions' warnings are mentioned for the data ingestion phase.
- Capability inventory: Generates Python scripts that use pandas, numpy, and matplotlib to read files and write results to the workspace (SKILL.md).
- Sanitization: No explicit data validation or content sanitization is described before processing data.
- [DYNAMIC_EXECUTION]: The skill's primary purpose is the generation of executable Python (.py) scripts from templates and method plans, which is a form of dynamic code generation.
- Evidence: Workflow steps 5, 8, and the Examples section describe generating multiple .py scripts and a run_summary.json using provided Python code templates (SKILL.md).
Audit Metadata