claude-cookbooks

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: 0.70). The cookbook includes examples and RAG workflows that explicitly fetch and process open web content (e.g., misc/read_web_pages_with_haiku.ipynb and third_party/Wikipedia/wikipedia-search-cookbook.ipynb), so the agent is expected to read and interpret untrusted public web and user-generated content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:26 PM