input-output-guardrails

Community

Enforce safety for AI inputs and outputs.

Authorpluginagentmarketplace
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill provides multi-layer safety to filter unsafe inputs and harmful outputs, reducing risk and ensuring policy compliance across AI interactions.

Core Features & Use Cases

  • Input guardrails: detect and block prompt injections, enforce length limits, and redact PII in user prompts.
  • Output guardrails: filter toxicity, mask sensitive data, and redact system-prompt leaks while offering safe fallbacks.
  • Use Case: Deploy in chatbots, coding assistants, and content-generation workflows to keep conversations compliant and safe.

Quick Start

To start using this skill, enable the Input/Output Guardrails in your AI workflow, load the provided guardrails configuration from assets/guardrails-config.yaml, and connect the skill to process every user message and subsequent AI responses.

Dependency Matrix

Required Modules

None required

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: input-output-guardrails
Download link: https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming/archive/main.zip#input-output-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 223,000+ vetted skills library on demand.