torch-geometric-graph-neural-networks
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides comprehensive documentation and code snippets for using the PyTorch Geometric (PyG) library. The content is strictly educational and technical, focusing on graph neural network architecture, data loading, and model training.
- [EXTERNAL_DOWNLOADS]: The skill references installation of standard machine learning libraries, including
torch,torch_geometric,pyg_lib,torch_scatter,torch_sparse,torch_cluster, andogb. These are well-known packages used within the data science community and are fetched from official package registries. - [INDIRECT_PROMPT_INJECTION]: The skill describes patterns for ingesting data from external sources, such as public graph datasets (e.g., Cora, ENZYMES) and custom CSV files for
InMemoryDatasetprocessing. While ingesting external data is a potential attack surface, the behavior documented here is a standard and necessary component of the machine learning workflow for which the skill is intended.
Audit Metadata