exa-search

Warn

Audited by Snyk on Feb 15, 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 explicitly performs web searches and uses WebFetch/mcp__exa__web_search_exa to find and extract full content from arbitrary URLs (see "Quick Reference: 'Read this URL: [link]' -> WebFetch" and "Integration Patterns: Discovery + Extraction"), so the agent will read untrusted third-party web content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 10:09 PM