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.pyusessubprocess.runto 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-CTMRrepository 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