gws-modelarmor-sanitize-response

Original：🇺🇸 English
Translated

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

11.0kinstalls
Sourcegoogleworkspace/cli
Added on

NPX Install

npx skill4agent add googleworkspace/cli gws-modelarmor-sanitize-response

Tags

Translated version includes tags in frontmatter
model-armorresponse-sanitizationai-safetygws-cligoogle-ai-tools

SKILL.md Content

View Translation Comparison →

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

bash
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

bash
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 — Global flags and auth
  • gws-modelarmor — All filter user-generated content for safety commands