MCP Integration

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly configures and connects to external hosted MCP servers via SSE/HTTP/WS (see examples/sse-server.json and examples/http-server.json with URLs like https://mcp.asana.com/sse and https://api.example.com/mcp), and agents/commands are documented to discover and consume those remote MCP tool outputs (via /mcp and tool calls), so the agent will ingest untrusted third‑party content returned by arbitrary external services.