modelarmor +sanitize-prompt
SkillAI & modelsLets your agent check a user prompt against Google Model Armor safety rules before sending it to a model.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the modelarmor +sanitize-prompt skill
About this capability
Google Model Armor: Sanitize a user prompt through a Model Armor template.
What this skill tells your AI
The instructions your AI receives, as published by googleworkspace/cli in skills/gws-modelarmor-sanitize-prompt/SKILL.md and read by ahel’s review.
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
Signals
- GitHub stars
- 31k
- Forks
- 2k
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
gws-modelarmor-sanitize-prompt- Source
- github.com/googleworkspace/cli