mcp-management

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly configures and uses MCP servers that fetch and analyze open web content—e.g., references to @modelcontextprotocol/server-brave-search, server-puppeteer, server-fetch in references/configuration.md and tools like playwright_screenshot_fullpage and eyes_read_document in assets/tools.json—so the agent will ingest and interpret untrusted/third-party URLs/pages as part of its workflow.