rag

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow and examples (SKILL.md Step 3 "Load documents from your source (file system, database, API)", the multi-source example using webRetriever, and references/document-chunking.md's "HTML Splitter" for web pages) explicitly ingest and retrieve content from web/APIs/public sources and then incorporate that content into retrieval-augmented prompts, which exposes the agent to untrusted third-party content that could enable indirect prompt injection.