← 返回 Skills 市场
lihengdao

weixin mp push 微信公众号图文生成与推送技能

作者 lihengdao · GitHub ↗ · v3.0.3 · MIT-0
cross-platform ⚠ suspicious
388
总下载
1
收藏
0
当前安装
28
版本数
在 OpenClaw 中安装
/install weixin-mp-push
功能描述
支持通过AI生成符合公众号规范的图文(文章和贴图),并推送到公众号草稿箱,兼容其它SKILL生成的图文、图片进行推送。通过配置向导扫码授权,支持多账号。无需泄露公众号Secret密钥,无需配置公众号IP白名单。
安全使用建议
What to check and do before installing: - Understand data flow: this skill sends the full HTML content and the user's openId (from config.json) to a third‑party API by default (https://api.pcloud.ac.cn/openClawService). If you are uncomfortable uploading draft content or identifiers to that endpoint, do not install or change apiBase to a trusted endpoint you control. - Inspect and control config.json: the skill requires you paste the configuration file into the skill directory. Check exactly what fields the config contains (openId, appId, etc.) and avoid including any secrets you don't want stored on disk. Consider storing config.json in a controlled location and reviewing its contents before running the script. - Be aware of destructive actions: documentation exposes a cleanupDrafts action (clearing the draft box). If the agent can invoke the skill autonomously, it could trigger deletions. Limit autonomous use or require explicit confirmation for destructive operations. - Prompt‑injection signal: SKILL.md contains unicode control characters that may be attempts to hide or alter instructions. Manually open SKILL.md in a trusted editor, remove any non‑printing/control characters, and verify the text matches expected instructions. - Verify the maintainer and endpoint: there is no homepage and the source is unknown. Confirm the identity and trustworthiness of the endpoint (api.pcloud.ac.cn) and the maintainer before uploading content or authorizing accounts. - Run in sandbox/least privilege: if you decide to try it, run the skill in a sandbox or test account first (not a production WeChat account), and avoid granting broad autonomous permissions until you are satisfied with behavior. If you want, I can: - highlight the exact lines in SKILL.md or push-to-wechat-mp.js that send data externally or create files - produce a safe checklist to sanitize config.json and remove control characters - suggest a minimally modified workflow that posts to your own server instead of the default apiBase
功能分析
Type: OpenClaw Skill Name: weixin-mp-push Version: 3.0.3 The skill bundle is designed to generate and push WeChat Official Account articles and images to a draft box. It utilizes a Node.js script (push-to-wechat-mp.js) to send content to a specific API endpoint (api.pcloud.ac.cn) using credentials obtained via a configuration wizard. The extensive instructions in Humanizer-zh.md and design.md are functional guidelines for the AI to improve content quality and formatting, with no evidence of malicious prompt injection, data exfiltration, or unauthorized execution.
能力评估
Purpose & Capability
技能声明的目标是生成并推送公众号图文;包含的脚本 (push-to-wechat-mp.js) 与 SKILL.md 的推送流程、配置文件要求及外部 API 调用相符。没有请求与该用途不相干的云凭据或高权限环境变量。
Instruction Scope
运行时指令要求将向导生成的 config.json(含 openId、accounts、可选 apiBase)保存到技能目录并将完整 HTML/封面(thumbImageContent)通过 POST 发送到第三方 apiBase(默认 https://api.pcloud.ac.cn/openClawService)。SKILL.md 还记录了能触发的清空草稿箱(cleanupDrafts)操作。说明文件中出现了 unicode 控制字符(prompt‑injection 信号),可能用于操控代理的行为或注入不可见指令。
Install Mechanism
无安装脚本或远程下载,只有打包的 JS 文件和文档(instruction-only + bundled code)。没有从不可信 URL 下载或在安装阶段写入额外二进制的行为,安装面较小。
Credentials
技能不要求环境变量或云密钥,但依赖用户把 config.json 放到技能目录:该文件含 openId、accounts 以及可自定义的 apiBase。将文章 HTML、封面 HTML 与 openId 传给第三方服务是功能需要但会泄露完整内容与用户标识到外部服务,用户应评估对该第三方的信任度。
Persistence & Privilege
技能不是 always:true;不会修改系统或其它技能配置. 但它会 persist(在技能目录)保存 config.json(含敏感标识 openId),并能通过远端接口执行可能破坏性操作(cleanupDrafts),所以在允许代理自主调用时需谨慎。
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install weixin-mp-push
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /weixin-mp-push 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v3.0.3
chore: sync (v3.0.3)
v3.0.2
chore: sync (v3.0.2)
v3.0.1
chore: sync (v3.0.1)
v3.0.0
chore: sync (v3.0.0)
v2.0.1
chore: sync (v2.0.1)
v2.0.0
chore: sync (v2.0.0)
v1.0.26
chore: sync (v1.0.26)
v1.0.25
chore: sync (v1.0.25)
v1.0.23
chore: sync (v1.0.23)
v1.0.22
chore: sync (v1.0.22)
v1.0.21
chore: sync (v1.0.21)
v1.0.20
chore: sync (v1.0.20)
v1.0.19
chore: sync (v1.0.19)
v1.0.18
chore: sync (v1.0.18)
v1.0.17
chore: sync (v1.0.17)
v1.0.16
chore: sync (v1.0.16)
v1.0.15
chore: sync (v1.0.15)
v1.0.12
chore: sync (v1.0.12)
v1.0.10
chore: sync (v1.0.10)
v1.0.9
chore: sync (v1.0.9)
元数据
Slug weixin-mp-push
版本 3.0.3
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 28
常见问题

weixin mp push 微信公众号图文生成与推送技能 是什么?

支持通过AI生成符合公众号规范的图文(文章和贴图),并推送到公众号草稿箱,兼容其它SKILL生成的图文、图片进行推送。通过配置向导扫码授权,支持多账号。无需泄露公众号Secret密钥,无需配置公众号IP白名单。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 388 次。

如何安装 weixin mp push 微信公众号图文生成与推送技能?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install weixin-mp-push」即可一键安装,无需额外配置。

weixin mp push 微信公众号图文生成与推送技能 是免费的吗?

是的,weixin mp push 微信公众号图文生成与推送技能 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

weixin mp push 微信公众号图文生成与推送技能 支持哪些平台?

weixin mp push 微信公众号图文生成与推送技能 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 weixin mp push 微信公众号图文生成与推送技能?

由 lihengdao(@lihengdao)开发并维护,当前版本 v3.0.3。

💬 留言讨论