wechat-auto-reply
ReviewAudited by ClawScan on May 10, 2026.
Overview
This skill is openly designed to read WeChat chats and send messages from your account, but its automatic-send path and external unreviewed installer deserve careful review before use.
Install only if you are comfortable with a tool reading WeChat conversations and sending messages from your account. Review the external Homebrew package first, test with a low-risk contact, and consider changing the workflow so every message requires confirmation.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A mistaken OCR result, wrong contact selection, or bad reply rule could send an unintended message from your WeChat account.
The skill documents a workflow that automatically sends WeChat messages based on OCR and confidence scoring without user confirmation in the high-confidence branch.
置信度 > 85% → 自动发送 ... 点击输入框获取焦点 ... 粘贴回复内容 ... 按回车发送
Use only with contacts where automatic replies are acceptable; ideally require confirmation before every send, preview the target/contact/message, and add an allowlist or dry-run mode.
Messages sent by the tool will appear to recipients as if you sent them yourself.
The skill uses the local logged-in WeChat application and sends messages under the user's existing WeChat identity.
tell application "WeChat" to activate ... 搜索联系人 → 直接发送指定消息
Verify the active WeChat account and contact before use, and avoid granting automation permissions on shared or unintended accounts.
Private WeChat conversation text is processed locally by the automation flow and may be shown in confirmation dialogs.
The workflow reads chat content from screenshots and may display the full recognized conversation for confirmation.
OCR 识别聊天内容 ... 低置信度时会显示完整聊天内容和建议回复
Avoid using it on highly sensitive chats unless you have reviewed how screenshots/OCR output are stored, logged, or discarded.
The actual installed command that controls WeChat is outside the provided scan context, so its implementation and updates were not verified here.
The reviewed artifact is instruction-only, but the documented setup pulls runnable code and dependencies from an external Homebrew tap.
brew install bjdzliu/openclaw/wechat-auto-reply ... 安装所有依赖（`cliclick`, `python@3`, `pyobjc`） ... 创建全局命令 `wechat-auto-reply`
Review the Homebrew formula and installed scripts before running, prefer pinned versions, and install only from a source you trust.