notebooklm
Warn
Audited by Snyk on Feb 15, 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 explicitly ingests and processes arbitrary public web content (e.g., "notebooklm source add 'https://...'", YouTube URLs, and "notebooklm source add-research" / "--from web") and then reads/indexes that content (source fulltext, citations, chat with references) as part of its workflow, exposing the agent to untrusted third-party input that could enable indirect prompt injection.
Audit Metadata