🎁 Get the FREE AI Skills Starter Guide β€” Subscribe β†’
BytesAgainBytesAgain
πŸ¦€ ClawHub

Gws Modelarmor Sanitize Response

by @googleworkspace-bot

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

Versionv1.0.12
Downloads727
Installs13
TERMINAL
clawhub install gws-modelarmor-sanitize-response

πŸ“– About This Skill


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 

Flags

| Flag | Required | Default | Description | |------|----------|---------|-------------| | --template | βœ“ | β€” | Full template resource name (projects/PROJECT/locations/LOCATION/templates/TEMPLATE) | | --text | β€” | β€” | Text content to sanitize | | --json | β€” | β€” | 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

  • gws-shared β€” Global flags and auth
  • gws-modelarmor β€” All filter user-generated content for safety commands
  • πŸ’‘ Examples

    gws modelarmor +sanitize-response --template projects/P/locations/L/templates/T --text 'model output'
    model_cmd | gws modelarmor +sanitize-response --template ...
    

    πŸ“‹ Tips & Best Practices

  • Use for outbound safety (model -> user).
  • For inbound safety (user -> model), use +sanitize-prompt.