Agent skill · security · googleworkspace
gws-modelarmor-sanitize-response
Google Model Armor: Sanitize a model response through a Model Armor template.
Why this skill is useful
Adds specific commands for sanitizing model responses that are not widely known or documented.
What it needs
Requires gws installed locally. About 1k tokens when loaded. Last updated 2026-08-01. 30,245 stars on the source repository.
What this skill does
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 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 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
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills googleworkspace/gws-modelarmor-sanitize-response