googleworkspace avatar

Gws Modelarmor Sanitize Response

googleworkspace/cli
20.2k

This skill sanitizes model responses using a specified Model Armor template to ensure outbound safety, making it suitable for AI agents and developers who need to filter and protect generated content. It offers key capabilities like applying templates to clean responses, with options for text or JSON input, and is primarily used to secure communication from models to users. It is designed for users working with AI models who require automated safety filtering for model outputs.

npx skills add https://github.com/googleworkspace/cli --skill gws-modelarmor-sanitize-response

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

GitHub Owner

Owner: googleworkspace

Files

gws-shared

gws-modelarmor

SKILL.md


name: gws-modelarmor-sanitize-response version: 1.0.0 description: "Google Model Armor: Sanitize a model response through a Model Armor template." metadata: 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

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

More skills