cremieux-cardio
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided medical data or study results to generate social media content.
- Ingestion points: User-supplied trial data or medical topics described in SKILL.md.
- Boundary markers: Absent.
- Capability inventory: Includes local Python execution for data visualization as shown in references/visualization-guide.md.
- Sanitization: Relies on the underlying model's standard processing.
- [DYNAMIC_EXECUTION]: The references/visualization-guide.md file provides Python code templates for the agent to generate charts.
- Evidence: Code snippets for matplotlib and numpy in references/visualization-guide.md.
- Impact: The templates are for standard data visualization tasks and do not involve untrusted input execution or network access.
Audit Metadata