The Agent Skills Directory

[SAFE]: The skill provides legitimate utility for clinicians to generate structured medical reports. The provided Python scripts (check_completeness.py, generate_template.py, timeline_generator.py, and validate_treatment_plan.py) perform standard file operations and regex-based validation without any suspicious network activity or sensitive file access.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external patient data to populate medical templates. While this introduces a potential ingestion surface for indirect prompt injection, the skill mitigates this risk through extensive instructions on HIPAA-compliant de-identification (Safe Harbor method) and the use of structured LaTeX environments that separate data from instructional logic. The capabilities are limited to document generation and validation, representing a low risk profile.

treatment-plans