weights-and-biases
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides standard documentation and code examples for integrating the Weights & Biases (wandb) library into machine learning workflows.
- [EXTERNAL_DOWNLOADS]: The skill references official Weights & Biases resources, documentation, and community links. These are well-known technology services and are documented neutrally for the purpose of tool integration.
- [COMMAND_EXECUTION]: Python code examples show expected usage of the
wandbAPI for logging metrics and managing artifacts. These operations are consistent with the skill's stated purpose of ML experiment tracking. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: Data is ingested via
run.use_artifact()andartifact.download()inreferences/artifacts.mdto retrieve datasets and model checkpoints. - Boundary markers: None explicitly shown in the code examples for delimiting untrusted artifact content, which is standard for library usage documentation.
- Capability inventory: The skill utilizes network operations for metric logging and file system operations for saving and loading model checkpoints via standard libraries (wandb, torch).
- Sanitization: Standard library functions are used for loading data and models, which is appropriate for the intended machine learning use cases.
Audit Metadata