gws-modelarmor-sanitize-response
Google Model Armor: Sanitize a model response through a Model Armor template.
Source facts
- Repository
- googleworkspace/cli
- Last source activity
- March 31, 2026 at 18:32
- Detected SKILL.md language
- English
- Stars
- 31,190
- Forks
- 1,854
Install options
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Review the source files
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Showing SKILL.md
SKILL.md
Source instructions ยท Read-only preview- 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":"[Truncated]"},"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` | โ | โ | Full template resource name (projects/PROJECT/locations/LOCATION/templates/TEMPLATE) |
| `--text` | โ | โ | Text content to sanitize |
| `--json` | โ | โ | 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) โ Global flags and auth
- [gws-modelarmor](../gws-modelarmor/SKILL.md) โ All filter user-generated content for safety commands
View on GitHub