deeplearning-ai-agentic-research-agent

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow uses external tools (e.g., Tavily web search / Wikipedia) to fetch and ingest outsider-authored web page content (public web content) into the agent’s LLM context during the “research” step.