Google Model Armor: Filter user-generated content for safety.
PREREQUISITE: Read
../gws-shared/SKILL.mdfor auth, global flags, and security rules. If missing, rungws generate-skillsto create it.
gws modelarmor <resource> <method> [flags]
| Command | Description |
|---------|-------------|
| +sanitize-prompt | Sanitize a user prompt through a Model Armor template |
| +sanitize-response | Sanitize a model response through a Model Armor template |
| +create-template | Create a new Model Armor template |
Before calling any API method, inspect it:
# Browse resources and methods
gws modelarmor --help
# Inspect a method's required params, types, and defaults
gws schema modelarmor.<resource>.<method>
Use gws schema output to build your --params and --json flags.
Copy a source-pinned command for your client. You run it yourself.
Destination: .claude/skills/gws-modelarmor · pinned to the source commit
# Run from your project root
git clone https://github.com/googleworkspace/cli.git .skillboard-tmp
git -C .skillboard-tmp checkout a3768d0e82ad83cca2da97724e46bea4ff0e6dbd
mkdir -p ".claude/skills"
cp -r ".skillboard-tmp/skills/gws-modelarmor" ".claude/skills/"
rm -rf .skillboard-tmpReview the source before running. This copies files into your project; it is not a one-click install and does not verify runtime safety.
sudo apt update && sudo apt install -y gitnpm install -g @anthropic-ai/claude-code# Run from your project root
git clone https://github.com/googleworkspace/cli.git .skillboard-tmp
git -C .skillboard-tmp checkout a3768d0e82ad83cca2da97724e46bea4ff0e6dbd
mkdir -p ".claude/skills"
cp -r ".skillboard-tmp/skills/gws-modelarmor" ".claude/skills/"
rm -rf .skillboard-tmpDestination: .claude/skills/gws-modelarmor
Scanner static-checks@0.1.0 · commit a3768d0e82ad. Static checks cannot prove runtime safety – review the source and the exact diff before installing. How checks work.
References parent-directory traversal, which can escape a target directory.
Evidence: ../· fingerprint fa08499e14d0113b