gws-modelarmor

Filter unsafe user-generated content across Google Workspace applications with the gws CLI.

8|3|Updated Feb 8, 2026
One-click install
npx skills add https://github.com/haberlah/dotfiles-claude --skill gws-modelarmor-haberlah
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gws-modelarmor
Source: https://github.com/haberlah/dotfiles-claude/tree/main/skills/gws-modelarmor
Command: npx skills add https://github.com/haberlah/dotfiles-claude --skill gws-modelarmor-haberlah

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Filter unsafe user-generated content within Google Workspace applications to prevent policy violations and protect users.

Core Features & Use Cases

  • Content filtering: Filter unsafe user-generated content across Google Docs, Sheets, Gmail, and Drive.
  • Policy enforcement: Enforce content-safety rules during creation, sharing, and collaboration.
  • Use Case: When moderating user submissions in Workspace apps, automatically evaluate for policy breaches and block unsafe content.

Quick Start

Run the gws modelarmor command with your target resource to begin enforcing safety rules.

Frequently Asked Questions about gws-modelarmor

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

FAQPage Schema
How do I filter unsafe user-generated content in Google Workspace?

Content filtering in Google Workspace applies safety rules to user submissions across Docs, Sheets, Gmail, and Drive, automatically blocking unsafe content during creation and collaboration workflows.

Does this content moderation approach work with Google Sheets and Gmail?

Yes, content moderation works with Google Sheets and Gmail, as well as Google Docs and Drive, enforcing safety policies during content creation, sharing, and collaboration across these Workspace applications.

How do I enforce content-safety policies during document collaboration?

You enforce content-safety policies during collaboration by running the modelarmor command against your target Workspace resources, which evaluates user-generated content for policy breaches and blocks unsafe material.

Do I need the gws CLI to automate content moderation workflows?

Yes, the gws CLI is required to automate content moderation workflows, providing the command interface to run modelarmor and apply safety rules to target Google Workspace resources.

What is the best way to prevent policy violations in Google Drive sharing?

The best way to prevent policy violations in Google Drive sharing is to apply automated content-safety rules that evaluate user-generated content for policy breaches during sharing and collaboration.

Can I block prompt injection attempts in user submissions?

Yes, you can block prompt injection attempts and other unsafe content by enforcing content-safety rules that automatically evaluate user submissions within your Google Workspace moderation workflows.