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 agentic CRAG workflow explicitly performs web fallbacks (see rules/agentic-corrective-rag.md where web_search uses tavily_client.search to fetch web pages and converts them into Document objects that are then fed into generation), so it ingests untrusted public web content that can influence agent decisions.