NotebookLM

Warn

Audited by Snyk on Mar 10, 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.md explicitly instructs adding and re-fetching arbitrary public sources (e.g., notebooklm source add "https://..."/YouTube, source add-research, source refresh, and client.sources.add_url in the Python examples), so the agent reads untrusted third‑party web/user-generated content as part of its workflow which can materially influence generated outputs and subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 06:56 AM