revit-api

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

• Third-party content exposure detected (high risk: 0.80). Flagged because the skill's Step 0 ("网络搜索验证：使用 WebSearch 搜索 Revit API + <技术概念>") explicitly requires performing WebSearch on the open web and extracting keywords from those search results, meaning the agent will fetch and read untrusted third‑party content as part of its workflow.