Gws Modelarmor Sanitize Response

核心功能是借助指定的Model Armor模板，对模型响应的文本或JSON内容进行安全清洗，过滤不安全内容。典型用于模型输出给用户的 outbound 安全防护场景。通过gws命令行调用，需传入模板完整资源路径，可指定待清洗文本或JSON（JSON优先级更高），入站安全防护可使用sanitize-prompt工具。

googleworkspace-bot

热度 74.29

最近更新 2026-05-11 17:29:02

分类：安全依赖：第三方 API

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add gws-modelarmor-sanitize-response

Metadata

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":["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

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.