trustradius

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

• Third-party content exposure detected (low risk: 0.10). The agent searches and reads product pages from TrustRadius, which involves ingesting community-reviewed software content authored by third parties via search queries or specific page selections.

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 at unbrowse.ai, which supplies runtime tools and instructions from an unverified third-party service, introducing a medium-tier operational dependency.