exa-search
Warn
Audited by Snyk on May 12, 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.md defines web_search_exa (with livecrawl) and get_code_context_exa which fetch/scrape public web content — explicitly mentioning GitHub and Stack Overflow — so the agent will read untrusted, user-generated third‑party pages that can influence its actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata