TopRank Skills

Home / Claw Skills / 其他 / gws-modelarmor-sanitize-response
Official OpenClaw rules 15%

gws-modelarmor-sanitize-response

Google Model Armor: Sanitize a model response through a Model Armor template.

Stars

0

Installs

0

Status

ACTIVE

Visibility

PUBLIC

安装方式

直接复制以下提示词,发送给你的 AI 助手即可完成安装。

请先检查是否已安装 SkillHub 商店,若未安装,请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店,然后安装 gws-modelarmor-sanitize-response 技能。 若已安装,则直接安装 gws-modelarmor-sanitize-response 技能。

Overview

Skill Key
googleworkspace-bot/gws-modelarmor-sanitize-response
Author
googleworkspace-bot
Source Repo
openclaw/skills
Version
1.0.0
Source Path
skills/googleworkspace-bot/gws-modelarmor-sanitize-response
Latest Commit SHA
901ed2d006114c00a3718ffa50ff2d84a5908920

Extracted Content

SKILL.md excerpt

# 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

Related Claw Skills