ai-rag-pipeline

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

• Third-party content exposure detected (high risk: 1.00). SKILL.md explicitly shows using tavily/search-assistant, exa/search and tavily/extract/exa/extract to fetch web search results and extract content from arbitrary public URLs and then directly injects those untrusted results into LLM prompts for summarization/analysis, so third‑party web content can materially influence agent actions.