note-meta-skill

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs NotebookLM to perform "Deep Research" searches and to add arbitrary public URLs or blogger articles (e.g., "notebooklm source add-research ... --mode deep", "notebooklm source add 'https://...'", and the example adding a blogger article), so the agent will ingest and interpret untrusted public/user-generated web content.