notebooklm

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill automatically opens and queries arbitrary NotebookLM notebooks (notebooklm.google.com) via scripts like scripts/ask_question.py and the "Smart Add" discovery flow in notebook_manager.py, ingesting user-uploaded / public third‑party content into the agent's workflow and thus enabling indirect prompt injection.

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

  • Potentially malicious external URL detected (high risk: 0.80). The skill opens and scrapes live NotebookLM pages at runtime (e.g., https://notebooklm.google.com or notebook URLs like https://notebooklm.google.com/notebook/...), and the fetched NotebookLM content is directly used as the agent's answer/context (i.e., it controls the prompts/responses the agent returns), making this an external runtime dependency the skill requires.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 11:37 PM