Model Armor: Sanitize a response for safety via the gws CLI.
From google-workspacenpx claudepluginhub grailautomation/claude-plugins --plugin google-workspaceThis skill uses the workspace's default tool permissions.
PREREQUISITE: Read
../gws-shared/SKILL.mdfor auth, global flags, and security rules. If missing, rungws generate-skillsto create it.
Sanitize a model response through a Model Armor template
gws modelarmor +sanitize-response --template <NAME>
| 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) |
gws modelarmor +sanitize-response --template projects/P/locations/L/templates/T --text 'model output'
model_cmd | gws modelarmor +sanitize-response --template ...