torch-geometric
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill serves as an educational reference for graph machine learning. All code patterns provided for defining neural networks, processing data, and implementing custom message-passing layers are standard for the PyTorch Geometric ecosystem.
- [EXTERNAL_DOWNLOADS]: References official dataset loading utilities and pre-trained models from well-known sources, such as the Hugging Face Hub and established research repositories. These operations are essential for the skill's functionality and target trusted infrastructure.
- [COMMAND_EXECUTION]: Provides instructions for standard Python package management using uv and pip, as well as distributed training configurations using PyTorch's DistributedDataParallel (DDP) and PyTorch Lightning. These are legitimate development workflows.
Audit Metadata