openai-agents-sdk

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

• Third-party content exposure detected (high risk: 0.90). The skill exposes agents to untrusted third-party content because it includes tools and patterns that fetch and summarize arbitrary web content (e.g., tools.md's async fetch_data(url), patterns.md's research_agent with search_web/search_academic/summarize_url, and the WebSearchTool hosted tool), so the agent is expected to read and interpret public URLs/search results as part of its workflow.