langchain4j-rag-implementation-patterns

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly includes UrlDocumentLoader.load(...) in references/references.md and shows RAG workflows in SKILL.md (e.g., EmbeddingStoreContentRetriever, SimpleRAGPipeline, and KnowledgeAssistant) that ingest and use retrieved web/document content as context to generate answers, meaning arbitrary third‑party web content can influence model behavior.