gws-modelarmor-sanitize-response

Sanitize AI model responses using a specified Google Model Armor template.

312|38|Updated Mar 4, 2026

Search Tags:#security #content filtering #ai safety #model armor #response sanitization

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps ensure that responses generated by AI models are safe and appropriate for end-users by sanitizing them through a defined Model Armor template.

Core Features & Use Cases

Response Sanitization: Applies a specified Model Armor template to clean and validate model outputs.
Outbound Safety: Primarily used to protect users from potentially harmful or inappropriate content generated by the model.
Use Case: After a model generates a customer service response, this Skill can run it through a template to remove any personally identifiable information or ensure it adheres to brand guidelines before being sent to the customer.

Quick Start

Sanitize the model's output using the template named 'my-safety-template'.

Frequently Asked Questions about gws-modelarmor-sanitize-response

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

FAQPage Schema

How do I sanitize AI model responses for outbound safety?▼

To sanitize AI model responses for outbound safety, you apply a specified Google Model Armor template to filter generated text content before it is presented to end users, removing sensitive or inappropriate information.

What is response sanitization for AI generated text?▼

Response sanitization is the process of cleaning and validating AI model outputs using a defined Model Armor template to ensure outbound safety and prevent the exposure of sensitive information or inappropriate language to end users.

How do I filter sensitive information from generated customer service responses?▼

You filter sensitive information from generated customer service responses by running the model output through a Model Armor template, which removes personally identifiable information and ensures adherence to safety guidelines before delivery.

Do I need a Model Armor template to filter generated text content?▼

Yes, you need a valid Model Armor template resource name for execution. The template defines the specific rules and filters applied to sanitize the AI model responses for outbound safety and compliance.

When do I need to sanitize model outputs for compliance?▼

You need to sanitize model outputs for compliance when presenting generated text content to users, particularly to prevent the exposure of sensitive information or inappropriate language in customer service or similar applications.

Can I use Model Armor to remove PII from AI outputs?▼

Yes, you can use Model Armor to remove PII from AI outputs by applying a specified template to sanitize the generated text, ensuring the outbound content adheres to brand guidelines and prevents sensitive information exposure.