Use Case
Agent Hardening is a powerful AI agent skill that extends your assistant with new capabilities. Test your agent's input sanitization against common injection attacks. Runs self-contained checks using synthetic test data only β no local files are accessed. This guide walks you through installing Agent Hardening, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install Agent Hardening: npx clawhub@latest --dir ~/.claude/skills install agent-hardening
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to data & analytics to trigger Agent Hardening
Review the output and refine your prompt for better results
Combine Agent Hardening with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Agent Hardening
Help me get started with Agent Hardening
What can Agent Hardening do for my data & analytics workflow?
Show me an example of using Agent Hardening
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install agent-hardeningOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install agent-hardeningβ 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/agent-hardening/π‘Extract and place the folder at the path above, then restart your agent.