notebooklm

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

• Third-party content exposure detected (low risk: 0.10). The workflow ingests arbitrary user-specified URLs and web research content into NotebookLM sources, which the agent subsequently queries via chat, fulltext retrieval, and generation tools.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the user/agent to install a third-party package (notebooklm-py) from PyPI and GitHub via pip, satisfying the dependency gate with a common/reputable unofficial publisher provenance at the medium tier.