Skills
.Work. You
Rest

agent-safety-guard

Community

Hardening AI agents with defense-in-depth.

Software Engineering#monitoring#defense-in-depth#ai#safety#red-team#prompt-injection#agent-security
Authorviliawang-pm
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Design and implement safety guardrails for AI agent systems. Use this skill when building production agents that need protection against prompt injection, jailbreaks, data leakage, uncontrolled tool use, and other adversarial attacks. Includes red-team testing checklists, defense-in-depth architectures, and monitoring strategies.

Core Features & Use Cases

  • Defense-in-depth architecture patterns across input, system, tool, and output layers
  • Red-team testing checklists and attack simulations
  • Monitoring, alerting, and governance for production agents
  • Use cases: auditing existing agents, designing safety for new agents, and incident response planning

Quick Start

Run the red-team checklist against your agent prototype to validate defenses.

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-safety-guard
Download link: https://github.com/viliawang-pm/ai-engineering-toolkit/archive/main.zip#agent-safety-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.