weights-and-biases
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a guide for using the official Weights & Biases (wandb) library for experiment tracking, model registry, and hyperparameter tuning. No malicious code or suspicious patterns were found.
- [EXTERNAL_DOWNLOADS]: The skill includes instructions to install the 'wandb' package from the official Python Package Index (PyPI) and demonstrates how to download user-defined artifacts from W&B servers.
- [DATA_EXFILTRATION]: While the skill demonstrates how to upload models and log metrics to the W&B platform, this is the intended primary function of the tool. There are no attempts to access or exfiltrate sensitive system files, credentials, or unauthorized data.
- [CREDENTIALS_UNSAFE]: The documentation mentions API key configuration but uses safe placeholders (e.g., 'your_api_key_here') and follows standard security practices for environment variables.
Audit Metadata