mcp-integration

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs Claude Code plugins to connect to external MCP servers (see references/server-types-and-patterns.md examples like "https://mcp.example.com/sse" and "https://api.example.com/mcp") and describes autonomous agent patterns that discover and call tools from those remote endpoints, so the agent will ingest and act on untrusted third-party content.