notebooklm
Warn
Audited by Snyk on Feb 17, 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). This skill programmatically opens and queries arbitrary NotebookLM notebook URLs (e.g., https://notebooklm.google.com/notebook/...) and ingests the returned answers—which the docs state may be derived from user-uploaded files and public web sources like websites, GitHub repos, and YouTube—so the agent reads and acts on untrusted, third-party content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill programmatically opens NotebookLM at runtime (e.g. https://notebooklm.google.com/notebook/...) and uses the fetched NotebookLM responses to drive follow-up prompts and final synthesized outputs, so external content from that URL directly controls the agent's behavior.
Audit Metadata