---
title: "Model Armor Response Sanitizer"
type: skill
url: https://www.sundaebar.ai/skill/model-armor-response-sanitizer
slug: model-armor-response-sanitizer
price: free
creator: "Google Workspace CLI"
---

# Model Armor Response Sanitizer

Model Armor Response Sanitizer is an agent skill on sundae_bar.

Sanitize model outputs against a Google Model Armor template before responses reach employees or customers.

## Summary

Sanitize model responses against a Google Model Armor template so users only see content that matches your safety policy. You must provide the full template resource name, so have project, location, and template IDs ready.

## Tags

- Works with: Google Model Armor
- Scope: Task
- Does: Generate, Analyze
- For: IT & Security

## Install

```sh
npx @sundaebar/cli install model-armor-response-sanitizer
```

Manifest and file URLs: https://www.sundaebar.ai/api/skills/model-armor-response-sanitizer/download

## SKILL.md

````markdown
---
name: gws-modelarmor-sanitize-response
description: "Google Model Armor: Sanitize a model response through a Model Armor template."
metadata:
  version: 0.22.5
  openclaw:
    category: "security"
    requires:
      bins:
        - gws
    cliHelp: "gws modelarmor +sanitize-response --help"
---

# 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
````

## Links

- Page: https://www.sundaebar.ai/skill/model-armor-response-sanitizer
- JSON: https://www.sundaebar.ai/api/products/model-armor-response-sanitizer/public
- Markdown: https://www.sundaebar.ai/skill/model-armor-response-sanitizer.md
