clinical-decision-support
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation includes instructions to install standard Python libraries (pandas, numpy, scipy, lifelines, matplotlib, pyyaml) from official package managers, which is normal for data-intensive clinical applications.
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to run internal Python scripts for data processing and report generation, following the expected workflow for a clinical document generator.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external CSV or JSON files for analysis, creating a theoretical attack surface for indirect prompt injection. However, this is mitigated by the included validation tool that checks for sensitive data and structural compliance.
Audit Metadata