rag

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s REQUIRED workflow is a RAG pipeline that ingests “Documents → Chunk … → Augment → Generate”; if those Documents come from outsider-authored sources (e.g., fetched public web pages, issue/wiki text, or user-provided external files), their readable chunk text is then placed into the LLM context under “Context: [1] … [2] …”.