ai-tutorials

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs (in the MCP section / Lesson 10 project task) to configure a Web Search MCP Server (e.g., brave-search) and "let AI autonomously search" public web content and organize it into local Markdown, which requires fetching and interpreting untrusted third‑party webpages that could influence subsequent actions.