The Agent Skills Directory

[SAFE]: The skill utilizes standard machine learning libraries, including torch, onnx, onnxsim, and onnxruntime, to perform model conversion and validation tasks.- [SAFE]: No network operations, external downloads, or requests to remote servers are present; all operations are performed on local files.- [SAFE]: File system access is restricted to reading local model weights and writing exported ONNX files in specified local directories, which is consistent with the skill's stated purpose.- [SAFE]: While torch.load is used for model loading (which involves deserialization), it is used with local path literals in a standard machine learning workflow, representing a common practice rather than a security risk in this context.

onnx_model_export