Gws Modelarmor Sanitize Prompt

Skill Verified Active

Google Model Armor: Sanitize a user prompt through a Model Armor template.

Purpose

To enhance AI safety by cleaning user prompts against predefined Model Armor templates before they are processed, preventing potential misuse or harmful content.

Features

Sanitize user prompts via Model Armor templates
Accepts text input or full JSON request body
Supports reading input from stdin
Integrates with Google Cloud Model Armor

Use Cases

When processing potentially untrusted user input that needs to be validated against a security template.
As a pre-processing step in AI agent workflows to ensure prompt safety.
To adhere to Google Cloud Model Armor policies for prompt handling.

Non-Goals

Sanitizing model responses (use `+sanitize-response` instead)
Providing AI Model Armor template management beyond basic usage
Operating independently of the `gws` CLI

Installation

npx skills add googleworkspace/cli

Runs the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.

Quality Score

Verified

99 /100

Analyzed about 19 hours ago

Trust Signals

Last commit2 days ago

GitHub owner googleworkspace

Stars26.2k

LicenseApache-2.0

Websitedevelopers.google.com

Status

View Source

Similar Extensions

Fixflow

100

Execute coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`). Support explicit commit policy overrides (`final_only`, `milestone`) and optional BDD (Given/When/Then) when users ask for behavior-driven delivery or requirements are unclear.

Skill

majiayu000