backend-fastify

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly registers an MCP server and /mcp endpoint (references/mcp-integration.md and src/mcp/server.ts / src/mcp/index.ts) that defines tools which accept and return arbitrary client-provided text (e.g., create_item content, set_preference, list_items) — untrusted third-party inputs that the agent will read/interpret and that can influence subsequent tool actions.