OpenClaw Profanity Plugin

Content moderation plugin for OpenClaw/Moltbot AI agents. Use when building chatbots that need profanity filtering, moderating user messages in Discord/Slack/Telegram bots, or adding content moderation to OpenClaw agents.

This skill appears to do what it says, but before installing the referenced npm package: 1) Inspect the package source on GitHub and npm for suspicious postinstall scripts or unexpected dependencies. 2) Confirm the package maintainer and recent activity (stars, issues, releases). 3) Review the onViolation handler examples — they call functions like banUser/trackViolation which you must implement safely (ensure they don't expose credentials or overreach). 4) Test the package in a sandboxed environment and pin a specific package version. 5) Be cautious if you deploy it to bots with moderator powers (deleting messages, banning users): require explicit review and logging for any automated punitive action.

Type: OpenClaw Skill Name: openclaw-profanity Version: 1.0.0 The provided files describe a profanity detection plugin for OpenClaw agents. The `_meta.json` contains standard metadata, and `SKILL.md` provides documentation and JavaScript code examples for integrating and configuring the plugin. There is no evidence of prompt injection against the AI agent, data exfiltration, malicious execution, persistence, or obfuscation within the analyzed content. The `npm install` command and external links are standard references to a third-party package, not malicious in themselves.