search-integration

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

• Third-party content exposure detected (high risk: 0.90). This Skill explicitly requires live external searches and ranks "公共网页搜索" and "社交媒体" as data sources in the SKILL.md (see "源优先级层级" / "Source priority" and the Execution/Trigger sections), meaning the agent will fetch and interpret public, user-generated third‑party content that can influence its actions.