Use Case
Input Guard is a powerful AI agent skill that extends your assistant with new capabilities. Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources. This guide walks you through installing Input Guard, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install Input Guard: npx clawhub@latest --dir ~/.claude/skills install input-guard
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to developer & devops to trigger Input Guard
Review the output and refine your prompt for better results
Combine Input Guard with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Input Guard
Help me get started with Input Guard
What can Input Guard do for my developer & devops workflow?
Show me an example of using Input Guard
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install input-guardOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install input-guardβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/input-guard/π‘Extract and place the folder at the path above, then restart your agent.