building-pydantic-ai-agents

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly adds and documents provider-native WebSearch/WebFetch capabilities and built-in tools (see SKILL.md "Use provider-native web search, web fetch" and references/BUILTIN-TOOLS.md showing WebSearchTool/WebFetchTool and duckduckgo_search_tool), which cause the agent to fetch and read untrusted public web content that can influence subsequent tool calls and decisions.