Google Workspace CLI 模型响应安全清理工具 | Model Armor sanitize-response 命令使用指南

gws-modelarmor-sanitize-response by googleworkspace/cli

6,000 周安装量

23,200 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/googleworkspace/cli --skill gws-modelarmor-sanitize-response

AI/机器学习自动化安全

🇨🇳中文介绍

modelarmor +sanitize-response

前提条件： 阅读 ../gws-shared/SKILL.md 了解身份验证、全局标志和安全规则。如果该文件缺失，请运行 gws generate-skills 来创建它。

通过 Model Armor 模板清理模型响应

用法

gws modelarmor +sanitize-response --template <NAME>

标志

标志	是否必需	默认值	描述
`--template`	✓	—	完整的模板资源名称 (projects/PROJECT/locations/LOCATION/templates/TEMPLATE)

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

🇺🇸English

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

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.

Google Workspace CLI 模型响应安全清理工具 | Model Armor sanitize-response 命令使用指南

🇨🇳中文介绍

modelarmor +sanitize-response

用法

标志

相关 Skills

示例

提示

另请参阅

🇺🇸English

modelarmor +sanitize-response

Usage

Flags

Examples

Tips

See Also

最新 Skills