guardrails-config

Official

Configure and deploy TrustyAI Guardrails for AI content safety on OpenShift

AuthorRHEcosystemAppEng
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill addresses the need for content safety and security on OpenShift AI platforms by configuring and deploying TrustyAI Guardrails Orchestrator.

Core Features & Use Cases

  • Content Safety: Set up content safety for LLM input/output content on OpenShift AI.
  • PII Detection: Configure PII detection on inference endpoints.
  • Prompt Injection Detection: Block prompt injection attacks.
  • Guarded Endpoint Validation: Validate guarded endpoints for safety checks.
  • Orchestration Policies: Define orchestration policies for blocking, warning, or passing through content.

Quick Start

Use the guardrails-config skill to configure and deploy Guardrails for your LLM endpoint.

Dependency Matrix

Required Modules

openshiftrhoai

Components

scriptsreferences

💻 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: guardrails-config
Download link: https://github.com/RHEcosystemAppEng/agentic-plugins/archive/main.zip#guardrails-config

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.