web-search-exa
Warn
Audited by Snyk on Jun 23, 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’s runtime workflow calls Exa web search/crawling endpoints (e.g.,
/search,/findSimilar,/contents, and/answer), which fetch and return outsider-authored page text from arbitrary URLs; that extracted free-form content is then provided to the agent/LLM as “context”/page contents for synthesis—an indirect prompt-injection exposure path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata