notebooklm
Warn
Audited by Snyk on Feb 16, 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 programmatically opens and scrapes arbitrary NotebookLM URLs (notebooklm.google.com) — e.g., scripts/ask_question.py and the "Smart Add" flow in notebook_manager.py — and ingests user-uploaded / public notebook content and NotebookLM answers (untrusted third-party user-generated data) as part of its normal workflow.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill programmatically opens user-supplied NotebookLM URLs (https://notebooklm.google.com/...) at runtime (ask_question.py / Smart Add) and uses the fetched notebook content and NotebookLM responses to generate metadata and drive follow-up prompts, so external content directly controls the agent's prompts and is a required runtime dependency.
Audit Metadata