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 includes explicit web ingestion (e.g., UrlDocumentLoader.load("https://example.com/doc.html") in references/references.md) and retrieval pipelines that feed retrieved third-party web/document content into the chat/retrieval workflow, exposing the agent to untrusted user-generated or public web content that could carry indirect prompt injections.