nv-segment-ctmr

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads source code from NVIDIA's official GitHub repository and model weights from the official Hugging Face repository. These downloads are from well-known technology providers and are consistent with the skill's stated purpose.
  • [COMMAND_EXECUTION]: The Python wrapper script uses subprocess.run() to execute the upstream MONAI bundle. Analysis of the implementation shows the command is constructed as a list of static arguments and validated inputs, effectively preventing shell command injection.
  • [SAFE]: The skill demonstrates standard development practices for medical imaging tools. It manages local file I/O within user-specified directories, uses standard libraries for image processing, and includes thorough error handling and output validation schema.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 04:35 PM
Security Audit — agent-trust-hub — nv-segment-ctmr