Skills
skills/promptingcompany/nv-skills/nv-generate-mr-brain-finetune/Gen Agent Trust Hub

nv-generate-mr-brain-finetune

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a legitimate workflow for medical AI research and development without any detected malicious patterns or security vulnerabilities.
  • [COMMAND_EXECUTION]: The main script scripts/run_mr_brain_finetune.py executes training and inference scripts using subprocess.run. These commands are constructed using static module names and validated local file paths, ensuring that user-provided inputs cannot be utilized for arbitrary command injection.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves dependencies and upstream code from github.com/NVIDIA-Medtech and downloads model assets from Hugging Face. These references target established organizations and well-known platforms recognized as standard for the model's ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 04:35 PM
Security Audit — agent-trust-hub — nv-generate-mr-brain-finetune