Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Sanitize a user prompt with Model Armor v1.0.0

Use this resource to sanitize a user prompt before sending it to a model

New

  • 319 downloads
  • 193 likes
  • 220 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install sanitize-prompt-model-armor

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent runs gws modelarmor +sanitize-prompt with the template's full name and the text, or a complete JSON body. You get the filtering result to plug into your call chain.

Mostly picked by

Updated November 2, 2026

Card for the “Sanitize a user prompt with Model Armor” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: --template, --text and --json options
  • SKILL.md: call examples and tips

Good fit for

  • You monitor the messages of a public chatbot
  • You test a filter template before going live

Not for

    Tags

    • prompt
    • security
    • model armor
    • filtering

    About

    You say

    “Run this prompt through the chatbot-client template and tell me whether it gets blocked.”

    Card for the “Sanitize a user prompt with Model Armor” skill

    Skill published by googleworkspace under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to sanitize a user prompt before sending it to a model
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md1.4 KB

    Origin and licence

    Listed unmodified

    Author
    googleworkspace
    Source
    github.com/googleworkspace/cli/tree/a3768d0e82ad83cca2da97724e46bea4ff0e6dbd/skills/gws-modelarmor-sanitize-prompt
    Licence
    Apache-2.0

    Notice

    « gws-modelarmor-sanitize-prompt » (googleworkspace, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.