exa-x-search
Warn
Audited by Snyk on Jun 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The skill calls an Exa MCP web search tool with
category: "tweet", which at runtime fetches outsider-authored tweet text from X/Twitter and feeds it back into the agent as readable “tweet content” in the tool results.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata