modelarmor +sanitize-response

SkillAI & models

Lets your agent check an AI model's response against a Model Armor safety template before using it.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the modelarmor +sanitize-response skill

About this capability

Google Model Armor: Sanitize a model response through a Model Armor template.

What this skill tells your AI

The instructions your AI receives, as published by googleworkspace/cli in skills/gws-modelarmor-sanitize-response/SKILL.md and read by ahel’s review.

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
--templateFull template resource name (projects/PROJECT/locations/LOCATION/templates/TEMPLATE)
--textText content to sanitize
--jsonFull 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

Signals

GitHub stars
31k
Forks
2k
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
gws-modelarmor-sanitize-response
Source
github.com/googleworkspace/cli