series-analyzer

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

• Third-party content exposure detected (high risk: 0.90). Yes — the skill's "联网搜索" step and the "联网搜索信息与市场反馈" / "热点讨论" outputs (and its version history listing WebSearch/Read) state it fetches audience reviews and social-media/forum discussions from the open web, so the agent will retrieve and interpret untrusted third-party user-generated content.