skills/open-edge-platform/physical-ai-studio/physicalai-train-exporting-and-validating/Gen Agent Trust Hub
physicalai-train-exporting-and-validating
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of documentation and workflow guidance for the physicalai library, focusing on exporting policies to various backends such as ONNX, OpenVINO, and ExecuTorch. All operations are restricted to the local library environment.- [SAFE]: No external network operations or remote code downloads were detected. All references point to local documentation files within the references/ directory.- [SAFE]: The execution patterns, including commands like physicalai export and uv run pytest, are standard for local development and testing of the library's own features and do not represent a security risk.- [SAFE]: No obfuscation, data exfiltration, or persistence mechanisms were found in the skill content. All metadata and instructional content align with the stated purpose of policy export and validation.
Audit Metadata