skills.rest
haberlah
haberlahCOMMUNITY
Explore all skills by this author →
GitHub

gws-modelarmor-sanitize-prompt

Sanitize user prompts with a Model Armor template via CLI.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Sanitize prompts to enforce safety and policy compliance before they reach the model using a Model Armor template.

Core Features & Use Cases

  • Sanitize user prompts via a Model Armor template to remove or neutralize unsafe content.
  • Works with a CLI workflow using --template and optional --text or --json for input.
  • Use Case: Integrate into content moderation pipelines or secure AI-assisted workflows.

Quick Start

Provide a sanitized prompt using the --template option with optional --text or --json input to filter user prompts safely.

Frequently Asked Questions about gws-modelarmor-sanitize-prompt

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

FAQPage Schema
How do I sanitize user prompts before sending them to an AI model?▼

You can sanitize prompts by applying a Model Armor template that filters and neutralizes unsafe content, enforcing safety and policy compliance before user input reaches the AI service.

What is the best way to enforce content moderation rules on AI prompts?▼

Enforcing content moderation on AI prompts involves using a Model Armor template to constrain user input, removing or neutralizing unsafe content before it is processed by the model.

How do I pass input text to a prompt sanitization filter?▼

You pass input to the prompt sanitization filter by using the --template flag with a full template resource name, and providing the input data via either the --text or --json flag.

Do I need a specific template name to filter user prompts for safety?▼

Yes, filtering user prompts for safety requires the --template flag populated with a full template resource name to apply the specific Model Armor safety rules to the input.

Can I use JSON input to drive prompt sanitization for policy enforcement?▼

Yes, you can use the --json flag to provide structured input data for prompt sanitization, allowing you to drive policy enforcement workflows within content moderation pipelines.

When should I use prompt sanitization in an AI-assisted workflow?▼

Use prompt sanitization in AI-assisted workflows when user input must be constrained or neutralized before reaching AI services, ensuring safe-guarded interactions and policy compliance.

Related Skills

Explore More Legal & Compliance Skills→
JetBrainsJetBrains
302

gws-modelarmor

Automate content filtering with Google Model Armor templates.

Official
Intermediate
jongwonyjongwony
4

gemini

Run Gemini prompts via CLI with model selection and approval modes.

Community
Advanced
niclasmartinsson-sysniclasmartinsson-sys
8

gws-modelarmor-create-template

Create a Google Model Armor template via the gws CLI with project, location, and template-id.

Community
Intermediate
m13vm13v
312

gws-modelarmor

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

Community
Intermediate