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: 1.00). The skill explicitly automates a browser to open and query user-provided NotebookLM URLs (see ask_question.py --notebook-url / "Smart Add" in SKILL.md) and ingests the notebookLM responses (public, user-uploaded/shared content on notebooklm.google.com) for the agent to read and synthesize, exposing it to untrusted third-party content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:03 AM