weights-and-biases
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation and use of the
wandbPython package. This is a widely used and reputable MLOps library for experiment tracking and model management. - [DATA_EXFILTRATION]: The skill describes methods for logging machine learning metrics and uploading model artifacts to the Weights & Biases platform (wandb.ai). This behavior is the intended primary purpose of the skill and uses standard API key management practices.
- [SAFE]: Analysis of the provided instructions and code snippets across all files (SKILL.md and references) shows no evidence of prompt injection, obfuscation, persistence mechanisms, or unauthorized privilege escalation. The content consists of legitimate technical documentation for a recognized developer tool.
Audit Metadata