pytorch-lightning

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's LightningDataModule examples (references/data_module.md and the DataModule/prepare_data examples) explicitly show downloading and ingesting datasets from public URLs (e.g., download_dataset("http://example.com/data.zip") / "Download data"), which means the agent is expected to fetch and read untrusted third‑party web content as part of its workflow.