Runs Claude's response through Google's Model Armor filters to catch hate speech, abuse, and safety violations before they reach users — without blocking legitimate use.
Best for: Teams shipping Claude in customer-facing products who need a safety layer.
Creator's repository · googleworkspace/cli
License: Apache-2.0
---
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