rag-architect

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

• Third-party content exposure detected (high risk: 0.85). The required workflow is a RAG architecture that retrieves and passes retrieved document text (e.g., r.payload.get("text", "") / r.text) into LLM context for generation/reranking, and those retrieved texts are outsider-authored content from the vector store (not authored by the operating user).