better-chatbot

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly loads and executes external MCP tools and built-in WebSearch/WebContent/Http tools that fetch and interpret content from arbitrary third‑party websites and services (see references/tool-system.md, references/ux-patterns.md and the Tool Lifecycle / loadMcpTools sections in api-architecture.md), so untrusted public web/social content can be ingested and directly influence tool calls and subsequent agent actions.