gws-modelarmor-sanitize-response

Sanitize model responses through Google Model Armor templates for outbound safety.

- Applies Model Armor templates to filter model outputs before delivery to users

- Accepts text input via --text flag or piped stdin, with optional full JSON request body override

- Requires template resource name in format projects/PROJECT/locations/LOCATION/templates/TEMPLATE

- Complements the +sanitize-prompt command for inbound user input safety

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)