skills.rest
cellarwood
cellarwoodOFFICIAL
Explore all skills by this author →
GitHub

gws-modelarmor-sanitize-response

Sanitize model responses using Google Model Armor templates.

Updated Apr 6, 2026
Search Tags:#template#safety#google#content-moderation#sanitize#gws#model-armor
One-click install
npx skills add https://github.com/cellarwood/figurio --skill gws-modelarmor-sanitize-response-cellarwood
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gws-modelarmor-sanitize-response
Source: https://github.com/cellarwood/figurio/tree/main/skills/gws-modelarmor-sanitize-response
Command: npx skills add https://github.com/cellarwood/figurio --skill gws-modelarmor-sanitize-response-cellarwood

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Sanitize model-generated responses to remove or redact unsafe, disallowed, or sensitive content before it reaches end users or downstream systems.

Core Features & Use Cases

  • Template-driven Sanitization: Execute a Google Model Armor template to enforce content safety policies on model outputs.
  • Flexible Input Handling: Accepts plain text or a full JSON request body to accommodate simple and complex model responses.
  • Use Case: Run as an outbound safety step to clean LLM responses in chatbots, content generation pipelines, or automated moderation workflows.

Quick Start

Run the gws modelarmor +sanitize-response command with a template resource name and the text to sanitize.

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 model outputs for unsafe content before displaying them to users?▼

To sanitize model outputs, you apply a Google Model Armor template that filters outbound responses to redact unsafe or disallowed content before it reaches end users or downstream systems.

What input formats does Google Model Armor content moderation accept for filtering responses?▼

Google Model Armor content moderation accepts both plain text and full JSON request bodies, allowing you to sanitize simple strings or complex model responses in automated moderation pipelines.

Do I need a specific template identifier to sanitize LLM responses with Model Armor?▼

Yes, you need a Google Model Armor template resource identifier in the projects/PROJECT/locations/LOCATION/templates/TEMPLATE format to execute the sanitization policies on your LLM responses.

When should I use outbound content moderation in my chatbot or generation pipeline?▼

Use outbound content moderation as a final safety step to clean LLM responses in chatbots, content generation pipelines, or automated workflows before delivering the text to user-facing interfaces.

Can I use Model Armor templates to redact sensitive information from automated moderation workflows?▼

Yes, Model Armor templates can redact sensitive or disallowed content from automated moderation workflows by executing template-driven sanitization policies on the generated model outputs.

What is the best way to filter outbound model responses for content safety policies?▼

The best way to filter outbound model responses is applying a Google Model Armor template, which enforces predefined content safety policies to sanitize text in chatbots and generation pipelines.

Related Skills

Explore More Software Engineering Skills→
haberlahhaberlah
8

gws-modelarmor-create-template

Create Google Model Armor templates with required project, location, and template-id flags.

Community
Intermediate
temple-slopetemple-slope

gws-modelarmor-sanitize-prompt

Sanitize user prompts by applying a Model Armor template.

Community
Intermediate
m13vm13v
312

gws-modelarmor-sanitize-response

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

Community
Basic
googleworkspacegoogleworkspace
30.3k

gws-modelarmor

Filter user-generated content with Google Model Armor templates.

Official
Intermediate