tavily-search
Warn
Audited by Snyk on Aug 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The tavily-search required runtime workflow performs web search and can include full page content snippets/raw text from third-party pages, so outsider-authored free text from search results is ingested by the LLM via the “search → extract → … → research” path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata