other-legal-retrieval

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

• Third-party content exposure detected (high risk: 0.72). 该技能的运行流程包含“多源信息检索/全文获取”，会从运行时的外部网页、数据库或官网抓取/读取非用户选择引入的公开文本（如监管案例、地方文件、学术文章等），这些外部自由文本可能携带间接提示注入内容进入LLM上下文。

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)