space-xhs-hotspot

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly requires emitting note URLs "原样输出" including the xsec_token query parameter (SKILL.md:15), which forces the LLM to reproduce token-like secrets verbatim in its output and creates an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). 该 skill 会将用户自述/生成的关键词用于调用红狐 API 获取小红书热门笔记列表，并在运行时把返回的笔记标题/简介/作者名等字段（外部作者撰写的自由文本）进入 LLM 进行“形态/钩子/高频词”等模式提取与汇总。