企业微信对话配置

Set up WeCom (企业微信) as a chat channel for OpenClaw using the official Tencent plugin with WebSocket long-polling. Use when user wants to connect WeCom bot, c...

Before installing: (1) verify the plugin package (@wecom/wecom-openclaw-plugin) source and review its code or repository/maintainer, because the skill itself provides no package files; (2) be aware you will need to provide a WeCom bot secret — the SKILL.md tells you to put it into ~/.openclaw/openclaw.json (plaintext), which may be readable by other local processes; consider using a secrets manager or environment variable if the platform supports it; (3) avoid enabling open allowFrom/ dmPolicy unless you intend the bot to be publicly reachable — prefer allowlist/pairing for production; (4) confirm your model provider has sufficient credits before connecting; (5) the skill metadata claims no required credentials but the instructions require a bot secret — ask the maintainer to clarify how secrets are stored and why metadata omits that requirement. If you cannot verify the plugin repository or are uncomfortable storing the secret in the config file, test in an isolated environment first.

Type: OpenClaw Skill Name: wecom-setup Version: 1.0.0 The skill provides instructions to set up a WeCom integration, which involves installing an external plugin (@wecom/wecom-openclaw-plugin) and configuring sensitive bot credentials (botId, secret). A significant concern is that SKILL.md explicitly instructs the AI agent to ignore security warnings related to 'Environment variable access combined with network send,' effectively coaching the agent to bypass platform security prompts. While the setup steps are consistent with the stated goal, the instruction to disregard security alerts is a high-risk indicator.