building-with-effect

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

• Third-party content exposure detected (high risk: 0.80). The skill's AI modules and agent examples (references/ai-modules.md — e.g., "Provider-Defined Tools" showing OpenAiTool.WebSearch and the "Chat with Tools (Agentic)" example) explicitly describe using provider web-search/tools that fetch and execute on open web results, meaning the agent would ingest untrusted third‑party content that can influence subsequent tool use and decision-making.