exa-search
Warn
Audited by Snyk on Jun 20, 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 is an Exa API–based semantic search tool, and at runtime it will fetch and ingest public web page text (outsider-authored content) returned by Exa into the agent’s LLM context for summarization/answering.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata