search

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The agent skill instructs the model to execute Exa search and web fetch operations to gather information from arbitrary public web pages.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill references external MCP server endpoints and authentication URLs (mcp.exa.ai, auth.exa.ai, dashboard.exa.ai) which act as operational runtime control planes and dependencies.