π³ Model Armor Sanitize Prompt (gws CLI)
Screen user prompts through a Google Model Armor template before they reach your model
- What
- Screen user prompts through a Google Model Armor template before they reach your model
- Cost
- Free
- Needs
- a paid Google Workspace account; the gws CLI installed and authenticated; a provisioned Model Armor template in a Google Cloud project; read the bundled gws-shared skill first for auth and security rules
- Install
- Copy the installer prompt below into your Muse β your agent does the rest.
π³ Requires a paid Google Workspace account for the gws CLI β no free tier. Curated by Skill Harbor β a real safety utility, not a gadget: it runs a user prompt through a Google Model Armor template (`gws modelarmor +sanitize-prompt --template projects/PROJECT/locations/LOCATION/templates/TEMPLATE`) with `--text`, `--json` or stdin input, and points at `+sanitize-response` for the outbound direction. No other fiche in the catalog covers Model Armor. By @googleworkspace, listed here with credit to its creator. Honest caveats: you need a provisioned Model Armor template in a Google Cloud project (the template resource name is required), the gws binary installed and authenticated, and the gws-shared skill read first for auth and security rules; sanitization is a screening layer, not a guarantee β it reduces risk, it doesn't eliminate it. Skill Harbor never reviews the code, review it yourself before use.
Version:
Quick answer
Model Armor Sanitize Prompt gws CLI is a free Muse skill, a safety utility, not a gadget: it runs a user prompt through a Google Model Armor template, with text, JSON or stdin input, and points at +sanitize-response. No other fiche covers Model Armor, and it requires a paid Google Workspace account for the gws CLI, with no free tier.
Install
Copy the install package below, then paste it into Museπ§ͺ Install ran in our test sandbox Β· Nov 11, 2026π Pinned version: commit a3768d0Step 0 β before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a paid Google Workspace account; the gws CLI installed and authenticated; a provisioned Model Armor template in a Google Cloud project; read the bundled gws-shared skill first for auth and security rules Install "Model Armor Sanitize Prompt (gws CLI)" for me. Screen user prompts through a Google Model Armor template before they reach your model Repository: https://raw.githubusercontent.com/googleworkspace/cli/a3768d0e82ad83cca2da97724e46bea4ff0e6dbd/skills/gws-modelarmor-sanitize-prompt/SKILL.md Pinned version: install the code at commit a3768d0e82ad83cca2da97724e46bea4ff0e6dbd exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file for the googleworkspace-gws-modelarmor-sanitize-prompt skill from the repository into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "googleworkspace-gws-modelarmor-sanitize-prompt". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. any accounts, API keys, or CLI tools mentioned in the prerequisites above). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. Never ask me to paste secrets in chat β credentials go through the secure vault or environment variables. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
π Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- a3768d0 Β· 2026-10-13
- Sandbox install test
- Install ran in our test sandbox Β· Nov 11, 2026 Β· Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked Β· Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you β no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the sellerβs own page, usually Stripe.
What does the β next to a creatorβs name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself β always check a skill before installing it.