google

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

• Third-party content exposure detected (low risk: 0.10). The agent uses search and retrieval tools on Google services (google.com, news.google.com, and business.google.com), which ingest search results and public web pages containing outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to connect to an external Model Context Protocol (MCP) server hosted at https://unbrowse.ai/mcp/google.com and execute REST calls against unbrowse.ai endpoints, which act as behavior-selecting configuration and operational tools supplied by a third-party unofficial publisher, resulting in a medium provenance risk.