---
name: gws-modelarmor-sanitize-prompt
description: "Google Model Armor: Sanitize a user prompt through a Model Armor template."
license: "Apache-2.0"
metadata:
  decimalai-skill-id: "39d06288-603c-46fb-a54a-bd17e8d8c07c"
  decimalai-version-id: "ece4f438-9e3d-457c-83d8-0449d737d108"
  decimalai-version: "1"
  decimalai-body-sha256: "025690f020ffb3f978e484abf6b544748853c5e9d1c4581bc060b60e3d8cbd6b"
  decimalai-name: "gws-modelarmor-sanitize-prompt"
  decimalai-format: "1"
  decimalai-invocation: "model"
  decimalai-category: "security"
  decimalai-source: "https://app.decimal.ai/s/gws-modelarmor-sanitize-prompt@1/SKILL.md"
---
# modelarmor +sanitize-prompt

> **PREREQUISITE:** Read `../gws-shared/SKILL.md` for auth, global flags, and security rules. If missing, run `gws generate-skills` to create it.

Sanitize a user prompt through a Model Armor template

## Usage

```bash
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

```bash
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](../gws-shared/SKILL.md) — Global flags and auth
- [gws-modelarmor](../gws-modelarmor/SKILL.md) — All filter user-generated content for safety commands