Pydantic AI Agent Builder

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

• Third-party content exposure detected (high risk: 0.90). The skill includes tools that perform web searches and fetch/analyze arbitrary external sources (e.g., search_web calling perform_search, search_sources/find_sources, and analyze_source calling fetch_content(source_url)), so the agent is expected to ingest untrusted public web content.