tavily

Warn

Audited by Snyk on Mar 16, 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). The skill explicitly calls the Tavily web API in scripts/search.mjs and scripts/extract.mjs to fetch/search public web pages (and arbitrary URLs) and prints AI-generated answers and extracted/raw content, meaning untrusted third-party content is ingested and can directly influence the agent's outputs and next actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 16, 2026, 09:56 AM
Issues
1