qdrant-vector-database-integration

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

• Third-party content exposure detected (high risk: 0.90). The skill ingests and uses arbitrary user-provided documents (untrusted third‑party content) via endpoints such as /api/rag/ingest and POST /api/search/document (RagController and SearchController) and then supplies that content to the LangChain4j content retriever/assistant for RAG, enabling indirect prompt injection.