# Gws Modelarmor Sanitize Response

> Google Model Armor: Sanitize a model response through a Model Armor template.

Source: https://skillsagentes.com/skills/googleworkspace/cli/gws-modelarmor-sanitize-response
Repository: https://github.com/googleworkspace/cli
Author: googleworkspace
License: Apache-2.0
Updated: hace 4 meses
Context cost: 19 tok installed, 359 tok once triggered, 359 tok with every bundled file
Bundle: 1 file, 1 KB
Permissions requested: none declared

## Install

```bash
npx -y skills add googleworkspace/cli --skill gws-modelarmor-sanitize-response --agent claude-code
```

## What it does

- Envía la respuesta de un modelo a través de una plantilla de Model Armor para sanitizarla antes de mostrarla al usuario
- Acepta texto directo (--text), JSON completo (--json) o entrada por stdin desde otro comando

## Use it when

- Necesitas verificar la seguridad de salida (model -> user) antes de mostrar la respuesta al usuario

## Don't bother when

- Necesitas verificar seguridad de entrada (user -> model); en ese caso usa +sanitize-prompt

## What triggers it

- "Sanitiza esta respuesta del modelo con la plantilla projects/P/locations/L/templates/T"
- "Pasa la salida de mi comando de modelo por Model Armor para revisar seguridad de salida"

## Before you install

- Requiere el binario gws configurado según gws-shared/SKILL.md (auth y flags globales) y una plantilla de Model Armor existente.

## Files

- SKILL.md — 1 KB

## SKILL.md

Reproduced verbatim from googleworkspace/cli under Apache-2.0. This section is the upstream document and is in English.

# modelarmor +sanitize-response

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

Sanitize a model response through a Model Armor template

## Usage

```bash
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

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

---

Skills Agentes — https://skillsagentes.com/skills/googleworkspace/cli/gws-modelarmor-sanitize-response