gws-modelarmor-sanitize-response
Lets your agent check AI responses with a safety model. Helps ensure AI outputs are safe and reliable.
What it does
This tool cleans and checks text generated by an AI to ensure it's safe and appropriate before being shown to anyone. It uses a predefined safety model for this verification.
When to use it
- ✓When you want to be sure the AI's response doesn't contain inappropriate content.
- ✓Before displaying an AI response to a customer or audience.
- ✓To apply specific safety rules to AI responses.
Example of what to ask your AI
“Clean this AI response using the 'my-safety-model' security template: [AI response here]”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
You provide the text the AI generated and the name of a safety model. The tool then uses this model to review the text and remove or flag any content that doesn't comply with the rules.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add googleworkspace/cli --skill gws-modelarmor-sanitize-responseOr download just the file:
curl -L https://raw.githubusercontent.com/googleworkspace/cli/main/skills/gws-modelarmor-sanitize-response/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
modelarmor +sanitize-response
PREREQUISITE: Read
../gws-shared/SKILL.mdfor auth, global flags, and security rules. If missing, rungws generate-skillsto create it.
Sanitize a model response through a Model Armor template
Usage
gws modelarmor +sanitize-response --template <NAME>
Flags
| Flag | Required | Default | Description |
|---|---|---|---|
--template |
✓ | — | Full template resource name (projects/PROJECT/locations/LOCATION/templates/TEMPLATE) |
--text |
— | — | Text content to sanitize |
--json |
— | — | Full JSON request body (overrides --text) |
Examples
gws modelarmor +sanitize-response --template projects/P/locations/L/templates/T --text 'model output'
model_cmd | gws modelarmor +sanitize-response --template ...
Tips
- Use for outbound safety (model -> user).
- For inbound safety (user -> model), use +sanitize-prompt.
See Also
- gws-shared — Global flags and auth
- gws-modelarmor — All filter user-generated content for safety commands
FAQ
What's the difference between 'sanitize-response' and 'sanitize-prompt'?
'Sanitize-response' is for checking what the AI will say to you (output). 'Sanitize-prompt' is for checking what you say to the AI (input).
What is a 'template'?
A 'template' is a set of safety rules you define to check text. It's like a custom filter.
Do I need to know how to code to use this?
No, you just need to know the command and the name of the safety model you want to use.
Details
Original description by the author
Google Model Armor: Sanitize a model response through a Model Armor template.
repo: googleworkspace/cli
Popularity
- GitHub stars
- 32k
- Ranking position
- #6277
- License
- Apache-2.0
- Updated
- 10/6/2026
Comments
- …
More skills from this repository
gws-admin-reports
Helps your agent get activity reports from Google Workspace. It collects audit and usage data.
googleworkspace/cli
gws-calendar-agenda
Helps your agent see upcoming events across all calendars. It's useful for organizing your schedule and knowing what's coming up.
googleworkspace/cli
gws-calendar-insert
Lets your agent create new events in Google Calendar. It's useful for scheduling appointments and meetings.
googleworkspace/cli
gws-calendar
Allows your agent to manage calendars and events. It's useful for organizing your life and work.
googleworkspace/cli
Similar skills
bengali-nlp
Has your agent process Bengali text. It helps understand and work with the language, normalizing text and handling its unique characteristics.
affaan-m/ECC
prompt-caching-strategy
Helps your agent optimize how it uses prompts for language models. It analyzes how prompts are made to find ways to cut costs and make responses faster by reusing information when possible.
affaan-m/ECC
prompt-optimizer
Has your agent analyze and improve the prompts you write. It suggests how to add information or change the wording so the AI model understands better and gives the desired answer.
affaan-m/ECC