domaindetails

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

• Third-party content exposure detected (low risk: 0.10). The agent retrieves external web pages and WHOIS/RDAP lookup results from domaindetails.com, which can contain untrusted third-party text or domain registration data.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill configures a remote Model Context Protocol (MCP) server running via HTTP (https://unbrowse.ai/mcp/domaindetails.com) which supplies executable tools and instructions governing agent behavior at runtime; because unbrowse.ai is a third-party unofficial intermediary service, this introduces a common/reputable unofficial operational dependency.