wandb-primary
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill interacts exclusively with the official Weights & Biases (
wandb) and Weave APIs to manage training data and GenAI traces. - [SAFE]: External package recommendations are limited to official library extras (e.g.,
wandb[workspaces]) installed via the user's preferred package manager. - [SAFE]: Robust instructions are provided to handle large datasets safely by processing them programmatically with pandas and numpy rather than dumping raw data into the LLM context, which mitigates risks associated with processing external data.
- [SAFE]: Helper scripts facilitate data transformation (e.g.,
unwrapfor Weave types) and diagnostic analysis using standard Python libraries without any unsafe dynamic code execution or privilege escalation.
Audit Metadata