notebooklm

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

• Third-party content exposure detected (low risk: 0.10). The agent queries user-provided or selected NotebookLM URLs using browser automation (ask_question.py), which ingests responses generated by the service based on uploaded documents. While external documents can be uploaded to NotebookLM, they are fetched via explicit user action or selected URLs rather than unsolicited monitored feeds.