gws-modelarmor-sanitize-prompt
Lets your agent clean and check user prompts with a safety model. Ensures user inputs are safe and appropriate.
What it does
This tool helps clean and prepare text you want to send to an artificial intelligence. It uses a predefined template to ensure the text is safe and appropriate.
When to use it
- ✓When you want to make sure your question to the AI won't cause issues.
- ✓Before sending sensitive information to the AI.
- ✓To standardize the format of questions for different AIs.
Example of what to ask your AI
“Clean my prompt: 'Tell me about the secrets of the universe.' using the 'universal-secrets-template'.”
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 you want to clean and the name of a cleaning template. The tool applies the rules of that template to your text.
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-promptOr download just the file:
curl -L https://raw.githubusercontent.com/googleworkspace/cli/main/skills/gws-modelarmor-sanitize-prompt/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
modelarmor +sanitize-prompt
PREREQUISITE: Read
../gws-shared/SKILL.mdfor auth, global flags, and security rules. If missing, rungws generate-skillsto create it.
Sanitize a user prompt through a Model Armor template
Usage
gws modelarmor +sanitize-prompt --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-prompt --template projects/P/locations/L/templates/T --text 'user input'
echo 'prompt' | gws modelarmor +sanitize-prompt --template ...
Tips
- If neither --text nor --json is given, reads from stdin.
- For outbound safety, use +sanitize-response instead.
See Also
- gws-shared — Global flags and auth
- gws-modelarmor — All filter user-generated content for safety commands
FAQ
What is a 'template'?
It's a set of predefined rules that the tool uses to clean your text.
What happens if I don't provide text?
The tool will read the text you type directly in the terminal or copy from elsewhere.
Can I use this to clean the AI's responses?
No, this tool is for cleaning what you send to the AI. To clean responses, use the '+sanitize-response' tool.
Details
Original description by the author
Google Model Armor: Sanitize a user prompt through a Model Armor template.
repo: googleworkspace/cli
Popularity
- GitHub stars
- 32k
- Ranking position
- #6276
- 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