tavily
Warn
Audited by Snyk on Feb 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: 1.00). The skill calls Tavily REST endpoints like /search, /extract, /map, and /crawl to fetch and return content (including raw_content) from arbitrary public URLs and web searches, so the agent ingests untrusted, user-generated third-party web content as part of its workflow.
Audit Metadata