clinical-reports

Pass

Audited by Gen Agent Trust Hub on May 29, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/generate_schematic.py utilizes the subprocess module to execute its helper script scripts/generate_schematic_ai.py. This is an internal execution pattern used to orchestrate the iterative AI generation and review process for scientific diagrams.
  • [EXTERNAL_DOWNLOADS]: The scripts/generate_schematic_ai.py script performs outbound network requests to openrouter.ai (a well-known LLM gateway) to utilize the Gemini 3.1 Pro and Flash models for image generation and quality review. This functionality is documented and requires a user-supplied API key.
  • [DATA_EXFILTRATION]: While the figure generation tool sends prompts to an external API, the skill provides extensive documentation and automated scripts (scripts/check_deidentification.py) specifically designed to help users remove sensitive HIPAA identifiers before processing data.
  • [SAFE]: The Python scripts included in the skill primarily focus on regex-based text validation and structured data extraction (e.g., scripts/extract_clinical_data.py), which are performed locally without executing or evaluating the content of the clinical reports.
Audit Metadata
Risk Level
SAFE
Analyzed
May 29, 2026, 12:31 PM
Security Audit — agent-trust-hub — clinical-reports