---
name: gws-modelarmor-sanitize-response
description: "Google Model Armor: Sanitize a model response through a Model Armor template."
license: "Apache-2.0"
metadata:
  decimalai-skill-id: "ef40588b-4e34-4755-bdd8-3d67225bf102"
  decimalai-version-id: "2fb38fb4-1c28-42ec-8b0d-eb8257b3b4e0"
  decimalai-version: "1"
  decimalai-body-sha256: "6ced21df800c339aaa3a79e3a3a200ce20a8458982d3b586211ba9d74a18cf01"
  decimalai-name: "gws-modelarmor-sanitize-response"
  decimalai-format: "1"
  decimalai-invocation: "model"
  decimalai-category: "security"
  decimalai-source: "https://app.decimal.ai/s/gws-modelarmor-sanitize-response@1/SKILL.md"
---
# 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