pytorch-lightning

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

• Third-party content exposure detected (high risk: 0.70). The skill's DataModule docs and Quick Workflow (references/data_module.md and SKILL.md "Prepare data" step) explicitly show using prepare_data() to download/process external datasets (e.g., download_dataset("http://example.com/data.zip")), so the agent is expected to fetch and ingest untrusted third‑party content that can materially influence training and subsequent actions.