gws-modelarmor-sanitize-response

Name: gws-modelarmor-sanitize-response
Author: googleworkspace

by googleworkspace23.4k975GitHub

Google Model Armor: Sanitize a model response through a Model Armor template.

Unlock Deep Analysis

Use AI to visualize the workflow and generate a realistic output preview for this skill.

Development

Compatible Agents

Claude Code

~/.claude/skills/

Codex CLI

~/.codex/skills/

Gemini CLI

~/.gemini/skills/

OpenCode

~/.opencode/skills/

OpenClaw

~/.openclaw/skills/

GitHub Copilot

~/.copilot/skills/

Cursor

~/.cursor/skills/

Windsurf

~/.codeium/windsurf/skills/

Cline

~/.cline/skills/

Roo Code

~/.roo/skills/

Kiro

~/.kiro/skills/

Junie

~/.junie/skills/

Augment Code

~/.augment/skills/

Warp

~/.warp/skills/

Goose

~/.config/goose/skills/

SKILL.md

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)

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.