clinical-decision-support
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute specific Python scripts located in the local scripts/ directory. A primary example is provided for diagram generation: python scripts/generate_schematic.py "your diagram description" -o figures/output.png.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface as it ingests and processes untrusted clinical data from external sources like EMRs or trial datasets.
- Ingestion points: The skill reads patient cohort data, biomarker profiles, and real-world evidence records from files or user input.
- Boundary markers: No explicit delimiters or instructions to disregard embedded commands in the clinical data are established.
- Capability inventory: The skill environment supports the execution of multiple analysis scripts (generate_survival_analysis.py, calculate_statistics.py, etc.) and has filesystem write access.
- Sanitization: There is no evidence of input validation or sanitization for the data being processed.
Audit Metadata