Home/数据 & AI/gws-modelarmor-sanitize-response
G

gws-modelarmor-sanitize-response

by @googleworkspacev
4.4(136)

Securely sanitizes model responses via Google Model Armor, ensuring safe and compliant output.

LLM Output FilteringAI SafetyResponse SanitizationGoogle WorkspaceContent ModerationGitHub
Installation
npx skills add googleworkspace/cli --skill gws-modelarmor-sanitize-response
compare_arrows

Before / After Comparison

1 组
Before

Directly using the model's raw responses may contain unsafe or inappropriate content, posing risks.

After

By sanitizing model responses with Model Armor templates, ensure safe and compliant output, avoiding potential issues.

description SKILL.md

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

FlagRequiredDefaultDescription
--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

forumUser Reviews (0)

Write a Review

Effect
Usability
Docs
Compatibility

No reviews yet

Statistics

Installs3.4K
Rating4.4 / 5.0
Version
Updated2026年4月29日
Comparisons1

User Rating

4.4(136)
5
24%
4
51%
3
24%
2
2%
1
0%

Rate this Skill

0.0

Compatible Platforms

🔧Claude Code
🔧OpenClaw
🔧OpenCode
🔧Codex
🔧Gemini CLI
🔧GitHub Copilot
🔧Amp
🔧Kimi CLI

Timeline

Created2026年3月16日
Last Updated2026年4月29日
🎁 Agent Knowledge Cards