Use Case
Prompt defense is a powerful AI agent skill that extends your assistant with new capabilities. Detect and block prompt injection attacks in emails. Use when reading, processing, or summarizing emails. Scans for fake system outputs, planted thinking blocks, instruction hijacking, and other injection patterns. Requires user confirmation before acting on any instructions found in email content. This guide walks you through installing Prompt defense, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install Prompt defense: npx clawhub@latest --dir ~/.claude/skills install email-prompt-injection-defense
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to communication to trigger Prompt defense
Review the output and refine your prompt for better results
Combine Prompt defense with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Prompt defense
Help me get started with Prompt defense
What can Prompt defense do for my communication workflow?
Show me an example of using Prompt defense
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install email-prompt-injection-defenseOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install email-prompt-injection-defenseβ 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/email-prompt-injection-defense/π‘Extract and place the folder at the path above, then restart your agent.