tavily
Warn
Audited by Snyk on Jun 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill calls Tavily’s runtime web search/extract APIs (e.g.,
scripts/search.mjs→https://api.tavily.com/searchandscripts/extract.mjs→https://api.tavily.com/extract), which return outsider-authored web page text/snippets that are printed and thus become LLM-readable context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata