notebooklm

Warn

Audited by Snyk on Apr 20, 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 ingests open web and user-generated content — e.g., SKILL.md and the CLI docs show commands like notebooklm source add "https://...", source add-research "query" --mode deep, adding YouTube/URL sources, retrieving source fulltext, and using those sources in ask/generate flows and background subagents, so untrusted third‑party content is read and can directly influence agent actions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 20, 2026, 12:40 AM
Issues
1