gws-modelarmor

Original source / Raw SKILL.md

---
name: gws-modelarmor
version: 1.0.0
description: "Google Model Armor: Filter user-generated content for safety."
metadata:
  openclaw:
    category: "productivity"
    requires:
      bins: ["gws"]
    cliHelp: "gws modelarmor --help"
---

# modelarmor (v1)

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

```bash
gws modelarmor <resource> <method> [flags]
```

## Helper Commands

| Command | Description |
|---------|-------------|
| [`+sanitize-prompt`](../gws-modelarmor-sanitize-prompt/SKILL.md) | Sanitize a user prompt through a Model Armor template |
| [`+sanitize-response`](../gws-modelarmor-sanitize-response/SKILL.md) | Sanitize a model response through a Model Armor template |
| [`+create-template`](../gws-modelarmor-create-template/SKILL.md) | Create a new Model Armor template |

## Discovering Commands

Before calling any API method, inspect it:

```bash
# Browse resources and methods
gws modelarmor --help

# Inspect a method's required params, types, and defaults
gws schema modelarmor.<resource>.<method>
```

Use `gws schema` output to build your `--params` and `--json` flags.



---

## Referenced Files

> The following files are referenced in this skill and included for context.

### ../gws-modelarmor-sanitize-prompt/SKILL.md

```markdown
---
name: gws-modelarmor-sanitize-prompt
version: 1.0.0
description: "Google Model Armor: Sanitize a user prompt through a Model Armor template."
metadata:
  openclaw:
    category: "security"
    requires:
      bins: ["gws"]
    cliHelp: "gws modelarmor +sanitize-prompt --help"
---

# modelarmor +sanitize-prompt

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

Sanitize a user prompt through a Model Armor template

## Usage

```bash
gws modelarmor +sanitize-prompt --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-prompt --template projects/P/locations/L/templates/T --text 'user input'
echo 'prompt' | gws modelarmor +sanitize-prompt --template ...
```

## Tips

- If neither --text nor --json is given, reads from stdin.
- For outbound safety, use +sanitize-response instead.

## 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

```

### ../gws-modelarmor-sanitize-response/SKILL.md

```markdown
---
name: gws-modelarmor-sanitize-response
version: 1.0.0
description: "Google Model Armor: Sanitize a model response through a Model Armor template."
metadata:
  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

```

### ../gws-modelarmor-create-template/SKILL.md

```markdown
---
name: gws-modelarmor-create-template
version: 1.0.0
description: "Google Model Armor: Create a new Model Armor template."
metadata:
  openclaw:
    category: "security"
    requires:
      bins: ["gws"]
    cliHelp: "gws modelarmor +create-template --help"
---

# modelarmor +create-template

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

Create a new Model Armor template

## Usage

```bash
gws modelarmor +create-template --project <PROJECT> --location <LOCATION> --template-id <ID>
```

## Flags

| Flag | Required | Default | Description |
|------|----------|---------|-------------|
| `--project` | ✓ | — | GCP project ID |
| `--location` | ✓ | — | GCP location (e.g. us-central1) |
| `--template-id` | ✓ | — | Template ID to create |
| `--preset` | — | — | Use a preset template: jailbreak |
| `--json` | — | — | JSON body for the template configuration (overrides --preset) |

## Examples

```bash
gws modelarmor +create-template --project P --location us-central1 --template-id my-tmpl --preset jailbreak
gws modelarmor +create-template --project P --location us-central1 --template-id my-tmpl --json '{...}'
```

## Tips

- Defaults to the jailbreak preset if neither --preset nor --json is given.
- Use the resulting template name with +sanitize-prompt and +sanitize-response.

> [!CAUTION]
> This is a **write** command — confirm with the user before executing.

## 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

```