space-wechat-layout

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill requires preserving and outputting the user's article verbatim (including asking the user to paste it) and explicitly copies the article's innerHTML to produce the final HTML, so any secrets embedded in the article would be reproduced verbatim by the LLM/output — creating a high exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md 的运行流程在“Collect the article”步骤中直接要求用户粘贴待排版的文章文本，并在后续“Prepare the content/Build the local preview”中将该文本转成可复制的 HTML（assets/static-preview-template.html 的 {{ARTICLE_HTML}} 被渲染并用于复制），因此外部作者可通过提供文章内容这一输入路径把任意免费文本注入到被 LLM 读取与处理的内容里。