nv-generate-mr-brain

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/run_mr_brain.py uses subprocess.run to execute the local Python inference script from the cloned upstream repository and to check Git commit hashes. This execution is the primary intended function of the skill and targets a known local path established by the skill's setup instructions.
  • [EXTERNAL_DOWNLOADS]: The skill clones the NVIDIA-Medtech/NV-Generate-CTMR repository from GitHub and downloads model weights from Hugging Face. These resources originate from well-known and trusted technology organizations and are necessary for the skill's synthetic data generation purpose.
  • [DATA_EXFILTRATION]: No unauthorized data exfiltration patterns were detected. Network activity is limited to resource acquisition from official model and code repositories as declared in the manifest.
  • [PROMPT_INJECTION]: The skill instructions and documentation provide operational guidance and do not contain patterns typical of prompt injection, role-play bypass, or instruction override attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 04:35 PM
Security Audit — agent-trust-hub — nv-generate-mr-brain