pai-work-with-datasets

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation and usage examples for the physicalai-train library and its CLI physicalai. All operations, including dataset loading via repo_id and training configuration, are standard practices within the intended domain of robotics machine learning.
  • [SAFE]: External links and repository references point to the official GitHub organization of the vendor (open-edge-platform), which is consistent with the skill's purpose.
  • [SAFE]: Data downloads from repo_id (e.g., lerobot/pusht) target HuggingFace, a well-known service for machine learning models and datasets. The skill explicitly advises users to ask before starting large transfers, promoting safe operation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 08:20 AM