space-xhs-account-audit

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires preserving and outputting full URLs containing xsec_token and shows CLI examples that include tokens (and references env vars to be supplied), which forces the LLM to handle or reproduce secret/session tokens verbatim in outputs.

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

• Third-party content exposure detected (medium risk: 0.30). 路径 A/B 在运行时会读取由用户提供的“小红书主页链接/截图”所对应的主页与笔记文字/标题/封面等内容进行分析，因此存在从外部（用户可选定的）文本注入到诊断流程的运行时摄入面。