gws-modelarmor-sanitize-prompt

Official

Sanitize user prompts with Model Armor.

Authorgoogleworkspace
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps ensure user-provided text is safe and compliant by running it through a predefined Google Model Armor template, preventing potentially harmful or inappropriate content from being processed.

Core Features & Use Cases

  • Prompt Sanitization: Cleanses user input against a specified Model Armor template.
  • Input Flexibility: Accepts text directly or via a full JSON request body.
  • Use Case: Before sending a user's query to a generative AI model, use this Skill to sanitize the prompt, ensuring it adheres to safety guidelines and doesn't contain malicious or policy-violating content.

Quick Start

Sanitize the user input 'What is the capital of France?' using the template 'projects/P/locations/L/templates/T'.

Dependency Matrix

Required Modules

None required

Components

references

💻 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: gws-modelarmor-sanitize-prompt
Download link: https://github.com/googleworkspace/cli/archive/main.zip#gws-modelarmor-sanitize-prompt

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.