food

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

• Third-party content exposure detected (low risk: 0.10). The agent searches food.com via Unbrowse MCP, returning recipe data and public content which constitutes low-risk outsider-authored content ingestion.

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 server hosted on an unverified third-party domain (unbrowse.ai) which acts as an operational dependency supplying behavior-selecting configuration and tool definitions at runtime.