"微信公众号草稿上传"

将本地 Markdown 文章上传到微信公众号草稿箱。当用户提到"上传文章到公众号"、"发布到微信公众号"、"推送到公众号草稿"等场景时应使用本技能。本技能通过调用微信公众平台 API，自动完成 Markdown 转 HTML、封面图生成/上传、创建草稿等全流程操作。

This skill appears to implement the advertised WeChat draft upload flow, but exercise caution before installing/ running it. Key points: - Do not run scripts/run_upload.py as-is. It hard-codes an AppID and AppSecret plus an absolute path; running it would use those embedded credentials. Treat those as accidental secrets. If those credentials are real, they should be revoked/rotated. - Prefer running scripts/upload_draft.py manually and provide your AppID/AppSecret and file paths on the command line as documented in SKILL.md. - Inspect and remove any hard-coded credentials from the repository. Search the repo for other secrets before use. - The scripts contact only expected endpoints: the official WeChat API hosts (api.weixin.qq.com) and a placeholder image host (placehold.co). If you require fully offline operation, provide a local cover image and do not allow network access. - Run in an isolated environment (or sandbox) the first time to confirm behavior and outputs, and review the saved draft_*.html files to verify no unexpected content is included. If you can provide confirmation that the embedded AppID/AppSecret are dummy/test values, confidence would increase; if they are valid, treat this as a credential leak and rotate them immediately.

Type: OpenClaw Skill Name: wechat-mp-draft-cnspica Version: 1.0.0 The skill bundle is classified as suspicious primarily due to the inclusion of `scripts/run_upload.py`, which contains hardcoded WeChat credentials (AppID and AppSecret) and specific local file paths, representing a significant security vulnerability and credential leak. This script also utilizes `exec()` to execute local code. While the core logic in `scripts/upload_draft.py` and `scripts/get_draft.py` appears to be a legitimate implementation for managing WeChat Official Account drafts via official APIs (api.weixin.qq.com), the inclusion of sensitive developer artifacts and insecure execution patterns makes the bundle risky for general use.