agent-mcp-cli

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

• Third-party content exposure detected (high risk: 0.70). The required runtime path is agent-mcp:call in remote mode, which POSTs to a configured /agent-mcp endpoint and ingests the returned JSON payload into the CLI/LLM context; that response is outsider-authored free text from an external server (not the operating user’s own tenant/app).