Sanitize an LLM response through Google Model Armor
Run model output through a Model Armor template with the gws CLI for outbound safety checks
- What
- Run model output through a Model Armor template with the gws CLI for outbound safety checks
- Cost
- Free
- Needs
- the gws CLI installed; a Google Cloud project with Model Armor enabled and an existing template; Model Armor screening is a paid GCP service (per-request billing)
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
💳 Paid API required — this skill drives Google Cloud's Model Armor through the gws CLI; Model Armor screening is billed per request, with no usable free tier stated. Curated by Skill Harbor — @googleworkspace's outbound-safety wrapper: sanitize a model response through a Model Armor template with `gws modelarmor +sanitize-response --template projects/PROJECT/locations/LOCATION/templates/TEMPLATE --text 'model output'` (or pipe model output into it, or pass a full JSON body), with companion coverage for inbound safety via `+sanitize-prompt`. By @googleworkspace, listed here with credit to its creator. Honest caveats: requires the gws CLI, a Google Cloud project with Model Armor enabled and an existing template; read the sibling gws-shared skill for auth and security rules before use; Apache-2.0 licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Sanitize an LLM response through Google Model Armor is a wrapper from @googleworkspace sanitizing responses through a Model Armor template, via gws modelarmor +sanitize-response with a template, text or JSON body, plus inbound +sanitize-prompt. It requires gws, a Cloud project with Model Armor enabled and a template; read gws-shared first for auth and security. Screening is billed per request.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit a3768d0Step 0 — 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: the gws CLI installed; a Google Cloud project with Model Armor enabled and an existing template; Model Armor screening is a paid GCP service (per-request billing) Install "Sanitize an LLM response through Google Model Armor" for me. It wraps `gws modelarmor +sanitize-response` to screen model output through a Model Armor template for outbound safety, with `+sanitize-prompt` as its inbound counterpart. Repository: https://raw.githubusercontent.com/googleworkspace/cli/a3768d0e82ad83cca2da97724e46bea4ff0e6dbd/skills/gws-modelarmor-sanitize-response/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 (and any helper files) from the repository path 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 "gws-modelarmor-sanitize-response". 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. authenticate the gws CLI; create a Model Armor template in the Google Cloud console if none exists yet — remember screening is billed per request). 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. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 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 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · 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
Model Armor
By the same creator, in the same series:
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 — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.