searching-internet-with-jina-ai

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly uses Jina AI public endpoints (s.jina.ai for web search and r.jina.ai/ to fetch readable text from arbitrary public URLs), so the agent will ingest untrusted third-party web content (search results and page text) that could contain injected instructions.