transformers
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or obfuscated code were detected across the skill files. The instructions align perfectly with the stated purpose of providing a developer utility for the Transformers library.
- [EXTERNAL_DOWNLOADS]: The skill installs core machine learning libraries including 'torch', 'transformers', and 'datasets'. These are legitimate, high-reputation packages from established organizations (PyTorch, Hugging Face) and are essential for the skill's functionality.
- [CREDENTIALS_UNSAFE]: The skill correctly handles authentication by directing users to use standard library methods like 'huggingface_hub.login()' or setting a 'HUGGINGFACE_TOKEN' environment variable. It does not contain any hardcoded secrets or attempt to exfiltrate user credentials.
Audit Metadata