mcp-media-inbox-triage

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

• Third-party content exposure detected (high risk: 0.95). The required workflow uses Zapier MCP to read outsider-authored Gmail message content (plain-text body and related fields) from a shared inbox at runtime, which the LLM then ingests for classification—this is classic email body text authored by non-operating-user parties (public/third-party communications) feeding into the model context.