Use Case
Guardian Shield is a powerful AI agent skill that extends your assistant with new capabilities. Locally scans untrusted text and documents to detect and block prompt injection threats, jailbreaks, exfiltration, and social engineering attacks. This guide walks you through installing Guardian Shield, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install Guardian Shield: npx clawhub@latest --dir ~/.claude/skills install guardian-shield
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to developer & devops to trigger Guardian Shield
Review the output and refine your prompt for better results
Combine Guardian Shield with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Guardian Shield
Help me get started with Guardian Shield
What can Guardian Shield do for my developer & devops workflow?
Show me an example of using Guardian Shield
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install guardian-shieldOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install guardian-shieldβ 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/guardian-shield/π‘Extract and place the folder at the path above, then restart your agent.