技能 人工智能 模型防护响应清洗

模型防护响应清洗

v20260401
gws-modelarmor-sanitize-response
通过 Model Armor 模板在命令行中清理模型响应,确保发向用户的输出符合安全策略。
获取技能
378 次下载
概览

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.

See Also

信息
Category 人工智能
Name gws-modelarmor-sanitize-response
版本 v20260401
大小 1.4KB
更新时间 2026-04-08
语言