Agent Guard

Real-time security framework for AI agents. Built in response to the Clinejection attack that compromised 4,000 developer machines through malicious GitHub issue titles.

What It Does

AgentGuard provides multi-layered pattern detection to catch prompt injection attacks before they hit your AI agents:

• Command injection detection - Catches npm install, curl | bash, rm -rf, etc.
• Prompt injection blocking - Detects "ignore previous instructions" and similar attacks
• Social engineering detection - Flags urgency-based manipulation ("emergency fix", "trust me")
• GitHub issue screening - Specialized detection for Clinejection-style attacks
• Real-time sanitization - Converts dangerous content to [BLOCKED_COMMAND] placeholders

Installation

As OpenClaw Skill