Gws modelarmor sanitize prompt
This skill should be used when the user says "sanitize a user prompt", "screen input for harmful content", "filter a user message before sending to AI", "run prompt through Model Armor", "check this input for safety", or wants to sanitize inbound user input through a Model Armor template. Covers text and JSON request bodies, and stdin input.From its SKILL.md
npx -y skills add RadOrigin-LLC/RAD-Claude-Skills --skill gws-modelarmor-sanitize-promptAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.7 KB, 296 tokens by cl100k_base, as published. Nobody here has run it
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
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.