task-prd-creator

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly requires fetching latest library docs via Context7 MCP (e.g., mcp_context7_get_library_docs calls for "/vercel/next.js" and "/nestjs/docs.nestjs.com"), which pulls public third‑party documentation that the agent will read and interpret as part of its workflow, exposing it to untrusted external content.