Skills
.Work. You
Rest

agent-guard

Community

Real-time AI security for agents.

Software Engineering#security#sanitization#mcp#analyze#ai-agents#openclaw#prompt-injection
Authorzscole
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Real-time detection and sanitization of prompt-injection and command-injection threats targeting AI agents, preventing unsafe prompts from altering behavior.

Core Features & Use Cases

  • Real-time detection of prompt and command injections
  • On-demand sanitization that replaces threats with safe placeholders
  • OpenClaw and Claude MCP server integration for seamless deployment
  • GitHub issue screening and threat analytics

Quick Start

Install the skill in your OpenClaw or Claude MCP environment and start analyzing text with agent-guard analyze to detect threats.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: agent-guard
Download link: https://github.com/zscole/AgentGuard/archive/main.zip#agent-guard

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.