rag-retrieval

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

• Third-party content exposure detected (high risk: 0.90). The skill's CRAG workflow (rules/agentic-corrective-rag.md) explicitly performs a web_search via tavily_client.search and ingests web results into Document(page_content=r["content"], metadata={"source": r["url"}), which the agent grades and uses to route/drive subsequent actions—i.e., it fetches and interprets untrusted public web content as part of its required workflow.