xhs-content-ops

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs extracting xsec_token from note URLs and embedding it verbatim as a --xsec-token command-line argument (and shows example commands), requiring the LLM/agent to handle and output a sensitive token directly.

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

• Third-party content exposure detected (medium risk: 0.30). 运行时路径在 scripts/fetch_note_content.ts 中：从用户/搜索选出的（并含 xsec_token 的）小红书笔记详情页读取 HTML/INITIAL_STATE__，解析出 title/desc/tags 等正文并写入 content.md，然后对这些外部文本进行后续对标分析。