treatment-plans
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to provide a structured workflow for medical documentation. All scripts and templates are transparent and serve legitimate clinical purposes.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a surface for processing untrusted data by ingesting patient information to populate templates. 1. Ingestion points: User-provided patient history and treatment details are interpolated into LaTeX templates. 2. Boundary markers: The skill includes strong HIPAA de-identification instructions, though lacks technical delimiters for untrusted input. 3. Capability inventory: The skill uses Bash, Write, and Edit tools to generate and validate files. 4. Sanitization: The provided scripts verify section completeness but do not perform input sanitization for LaTeX injection.
Audit Metadata