painpoint-validate

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required workflow includes “检索用户抱怨、评论、GitHub Issues、社区反馈、竞品缺陷” and “如果 Web Search is required…执行搜索/记录外部证据”，so at runtime it may ingest outsider-authored free text from public web pages or community discussions into the LLM context via the Web Search/retrieval step.