ai-tutorials

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

• Third-party content exposure detected (high risk: 0.90). The syllabus and Step 10 project task explicitly instruct configuring a Web Search MCP Server and letting the agent autonomously search and ingest public web content (e.g., "configure Web Search and Filesystem MCP Server, let AI autonomously search"), which means the agent will fetch and interpret untrusted third‑party webpages as part of its workflow.