ai-gateway-guardrails

Official

Secure LLM Gateway with Advanced Guardrails

Authoraws-samples
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides robust security for the LLM Gateway, addressing concerns like PII redaction, prompt injection defense, jailbreak detection, toxicity filtering, and tool allow-listing.

Core Features & Use Cases

  • Input/Output Guardrails: Implements guardrails at the LLM Gateway layer to protect against data breaches and unauthorized actions.
  • Compliance with ISMS-P: Designed for environments like finance, healthcare, and public sectors that require strict compliance.
  • Integration with Guardrails: Integrates Bedrock Guardrails, NeMo Guardrails, Llama Guard 3, and regex/regex-ML policies.

Quick Start

Activate the skill and define the guardrails configuration for your LLM Gateway.

Dependency Matrix

Required Modules

bedrocknemo-guardrailsllama-guard-3regex-ml

Components

scriptsreferencesassets

💻 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: ai-gateway-guardrails
Download link: https://github.com/aws-samples/sample-oh-my-aidlcops/archive/main.zip#ai-gateway-guardrails

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 620,000+ vetted skills library on demand.