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: 1.00). The skill explicitly automates a browser to open and scrape NotebookLM pages (see ask_question.py and SKILL.md instructions referencing https://notebooklm.google.com/notebook/...), consuming user-uploaded/public NotebookLM content and using those responses to drive follow-up questions and final answers, so untrusted third-party content can materially influence agent behavior.

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

  • Potentially malicious external URL detected (high risk: 0.80). The skill navigates to and scrapes NotebookLM at https://notebooklm.google.com/... at runtime (page.goto / wait_for_url) and injects that fetched notebook content into its answers, meaning external content from that URL directly influences the agent's outputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 03:57 AM