Agent Skills
› googleworkspace/cli
› gws-modelarmor-sanitize-response
gws-modelarmor-sanitize-response
GitHub通过 Model Armor 模板对模型输出内容进行安全清洗，适用于出站场景（模型到用户），支持文本或 JSON 输入。
触发场景
需要过滤或净化 AI 模型生成的响应内容
执行出站安全检查以保护终端用户
安装
npx skills add googleworkspace/cli --skill gws-modelarmor-sanitize-response -g -y
SKILL.md
Frontmatter
{
"name": "gws-modelarmor-sanitize-response",
"metadata": {
"version": "0.22.5",
"openclaw": {
"cliHelp": "gws modelarmor +sanitize-response --help",
"category": "security",
"requires": {
"bins": [
"gws"
]
}
}
},
"description": "Google Model Armor: Sanitize a model response through a Model Armor template."
}
modelarmor +sanitize-response
PREREQUISITE: Read
../gws-shared/SKILL.mdfor auth, global flags, and security rules. If missing, rungws generate-skillsto create it.
Sanitize a model response through a Model Armor template
Usage
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
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 — Global flags and auth
- gws-modelarmor — All filter user-generated content for safety commands
版本历史
- a3768d0 当前 2026-08-20 07:24
