tavily

Warn

Audited by Snyk on Mar 1, 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 fetches and ingests content from arbitrary public web pages via the Tavily API (see scripts/extract.mjs which extracts raw_content from user-supplied URLs and scripts/search.mjs which queries https://api.tavily.com/search and prints AI-generated answers and content snippets), so untrusted third-party content can directly influence agent outputs and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 08:34 AM