tavily-web
Warn
Audited by Snyk on Aug 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill “tavily-web” performs web search/content extraction/crawling via the Tavily API, which can ingest outsider-authored free text from arbitrary web content that the agent actively fetches based on user/task inputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata