food

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires real-time checks against public web sources (map POIs such as 高德/百度地图 and consumer platforms like 大众点评/美团, plus official websites/公众号 and other public pages), so the agent will fetch and interpret untrusted, user-generated/open-web content as part of its workflow.