pyhealth

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references synthetic healthcare datasets hosted on Google Cloud Storage (https://storage.googleapis.com/pyhealth/Synthetic_MIMIC-III/). This is an official resource provided by the PyHealth developers for demonstration and educational purposes.
  • [EXTERNAL_DOWNLOADS]: Installation instructions include the official PyTorch wheel index (https://download.pytorch.org/whl/cu121) for CUDA support, which is a trusted source for Python packages.
  • [COMMAND_EXECUTION]: The documentation provides standard development commands using the uv package manager and python interpreter. These instructions are used to initialize projects, manage dependencies, and execute training scripts locally.
  • [SAFE]: No malicious patterns such as prompt injection, obfuscation, or unauthorized data exfiltration were detected. The skill correctly advises users on handling sensitive clinical data (MIMIC-III/IV) by pointing to local directories after proper credentialing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 09:23 AM
Security Audit — agent-trust-hub — pyhealth