gws-modelarmor

Filter user-generated content and model responses with Google's Model Armor templates.

312|38|Updated Mar 4, 2026

Search Tags:#compliance #safety #content moderation #model armor #prompt sanitization #response filtering

Ready to run

npx skills add https://github.com/m13v/fazm --skill gws-modelarmor

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gws-modelarmor
Source: https://github.com/m13v/fazm/tree/main/skills/gws-modelarmor
Command: npx skills add https://github.com/m13v/fazm --skill gws-modelarmor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps ensure user-generated content and AI responses are safe and adhere to specific guidelines by using Google's Model Armor.

Core Features & Use Cases

Content Sanitization: Filter prompts and responses through predefined Model Armor templates to detect and mitigate harmful or inappropriate content.
Template Management: Create and manage custom Model Armor templates for tailored safety policies.
Use Case: Before displaying a user's comment on a public forum, use this Skill to sanitize it, preventing the display of offensive language or personal information.

Quick Start

Use the gws modelarmor skill to sanitize a user prompt using the default template.

Frequently Asked Questions about gws-modelarmor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I filter user-generated content for safety and policy compliance?▼

You filter user-generated content for safety and policy compliance by passing it through predefined Model Armor templates to detect and mitigate inappropriate text before public display.

How does prompt sanitization prevent prompt injection attacks?▼

Prompt sanitization prevents prompt injection by filtering user inputs through Google's Model Armor templates, removing malicious instructions and validating content before the model processes the request.

Do I need the gws CLI tool to use Model Armor for content moderation?▼

Yes, you need the gws CLI tool installed and pre-configured Model Armor templates set up to perform content moderation, prompt sanitization, and response validation.

Can I create custom Model Armor templates for tailored safety policies?▼

Yes, you can create and manage custom Model Armor templates to establish tailored safety policies for content moderation and response validation within your specific application context.

What is the best way to validate AI model responses for inappropriate content?▼

The best way to validate AI model responses is by filtering them through Model Armor templates to ensure outputs adhere to safety guidelines and policy compliance before end-user delivery.

When should I use response filtering for content moderation in my application?▼

You should use response filtering for content moderation in applications requiring strict safety policies, such as public forums displaying user comments, to prevent offensive language or personal information exposure.