research-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly uses "搜索信息
• 使用 web search 获取信息", meaning the agent will fetch and read open web content (public websites) as part of its research, exposing it to untrusted third-party/user-generated material.