ai-rag-patterns

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

• Third-party content exposure detected (high risk: 0.80). This skill's workflow explicitly routes queries to external web search and resolves citation URLs (see "Stage 3 — Modular RAG" and the router options in references/production-rag.md and the "Edge Cases"/"Fallback: web search tool" entries), which means the agent is expected to fetch and interpret open/public third‑party content that could carry untrusted, user-generated instructions.