gws-modelarmor-sanitize-prompt
Google Model Armor: Sanitize a user prompt through a Model Armor template.
pinned to #a3768d0updated 3 days ago
Ask your AI client: “install skills/gws-modelarmor-sanitize-prompt”.
Requires the metahub MCP server installed in your client. Set up MCP.
mh install skills/gws-modelarmor-sanitize-promptmetahub onboarded this repo on the author's behalf.
If you own github.com/googleworkspace/cli on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.
Stars
30,273
Last commit
3 days ago
Latest release
published
- #agent-skills
- #ai-agent
- #automation
- #cli
- #discovery-api
- #gemini-cli-extension
- #google-admin
- #google-api
- #google-calendar
- #google-chat
- #google-docs
- #google-drive
- #google-sheets
- #google-workspace
- #oauth2
- #rust
About this skill
Pulled from SKILL.md at publish time.
PREREQUISITE: Read ../gws-shared/SKILL.md for auth, global flags, and security rules. If missing, run gws generate-skills to create it.
Evaluation report
WarningsAutomated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.a3768d0· 3 days ago
Documentation
7 passed2 warningsDescription qualitywarn
12 words · 74 chars — skills use the description as their trigger; aim higher
Aim for 15+ words and include trigger phrases like “use this skill when …”.
Homepage or repository declaredwarn
No homepage or repository declared.
Add a "homepage" or "repository" field to SKILL.md.
README is present and substantial
20,235 chars · 16 sections · 22 code blocks
Tags / topics declared
16 total — agent-skills, ai-agent, automation, cli, discovery-api, gemini-cli-extension (+10)
README has usage / example sections
found: Installation · Quick Start
Homepage / docs URL declared
https://developers.google.com/workspace
Description is substantive
Description is 12 words.
Documentation present and substantive
Documentation present (SKILL.md, 183 words).
Documentation shows usage
Documentation includes 2 code examples.
Release history
1- releasecurrenta3768d0warn3 days ago
Contents
PREREQUISITE: Read
../gws-shared/SKILL.mdfor auth, global flags, and security rules. If missing, rungws generate-skillsto create it.
Sanitize a user prompt through a Model Armor template
Usage
gws modelarmor +sanitize-prompt --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-prompt --template projects/P/locations/L/templates/T --text 'user input'
echo 'prompt' | gws modelarmor +sanitize-prompt --template ...
Tips
- If neither --text nor --json is given, reads from stdin.
- For outbound safety, use +sanitize-response instead.
See Also
- gws-shared — Global flags and auth
- gws-modelarmor — All filter user-generated content for safety commands
Reviews
No reviews yet. Be the first.
Related
Verification Before Completion
Evidence before assertions, always
Writing Plans
Turn specs into phased implementation plans
Test-Driven Development
Red → green → refactor discipline for any feature or bugfix
mh install skills/gws-modelarmor-sanitize-prompt