nanogpt
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No indicators of malicious behavior, prompt injection, or data exfiltration were found in the skill contents or metadata.
- [EXTERNAL_DOWNLOADS] (LOW): The skill instructs the user to install standard machine learning libraries (torch, transformers, datasets) from PyPI and download datasets from HuggingFace. These are trusted sources within the AI research community.
- [COMMAND_EXECUTION] (SAFE): Command execution is limited to standard Python script invocations for data preparation, model training, and text sampling.
Audit Metadata