Gws Modelarmor Sanitize Response
googleworkspace/cliOfficial
The gws-modelarmor-sanitize-response skill allows Google Workspace CLI users to filter model-generated responses through a Model Armor template to ensure outbound safety before content reaches end users. It accepts model output via command-line flags or standard input and applies configured safety policies to detect and sanitize potentially harmful content. This skill is designed for developers integrating AI models into Google Workspace applications who need to implement outbound content filtering as part of their safety pipeline.
- installs
- 29.6K
- GitHub stars
- 31.9K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add googleworkspace/cli --skill gws-modelarmor-sanitize-response --agent claude-codeInstalls into .claude/skills of the current project.
Files
modelarmor +sanitize-response
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
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
- gws-shared — Global flags and auth
- gws-modelarmor — All filter user-generated content for safety commands
Sponsors
Details
- Repository
- github.com/googleworkspace/cli
- Categories
- CLI & Terminal, Office & Documents
