transformers
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): The skill documentation and provided code snippets follow standard industry practices for the Transformers library. No malicious code or patterns were detected.
- Credentials Unsafe (SAFE): The skill references the use of a HUGGINGFACE_TOKEN, but only provides a placeholder string for illustrative purposes, which is not a security risk.
- Indirect Prompt Injection (SAFE): While the skill processes external text data, this is its primary intended function. The documentation demonstrates standard usage without bypassing safety filters.
- Ingestion points: Text inputs in pipeline and generation examples in
SKILL.mdandreferences/pipelines.md. - Boundary markers: Not explicitly used in examples.
- Capability inventory: Model inference and fine-tuning via
transformerslibrary. - Sanitization: Relies on the underlying model's behavior.
Audit Metadata