xhs-business-validator

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to ask the user for API tokens and to write/read them into a local .env and to use them in Authorization headers (and even to construct curl requests), which means the agent will receive and may need to emit secret values verbatim (e.g., when writing .env or embedding tokens in commands), creating an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). runtime 路径在 SKILL.md 的工作流 Step 1/2：先通过 TikHub API（对外部公开笔记/评论进行搜索与拉取）读取小红书笔记与评论中的 desc/content 等自由文本，再在 Step 3 进行 AI 分析。