AutoGineer
Generated banner for Gws Modelarmor Sanitize Prompt
Generated logo for Gws Modelarmor Sanitize Prompt

Gws Modelarmor Sanitize Prompt

Google WorkspaceOfficialPublished by Google Workspace

  • Skill
  • Tool integration
  • Security
  • Apache-2.0
  • No issues found
Download ZIP

From the author

Google Model Armor: Sanitize a user prompt through a Model Armor template.
— the description by Google Workspace

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The gws-modelarmor-sanitize-prompt skill provides a command-line interface to interact with Google Model Armor for the purpose of sanitizing user-provided text or JSON payloads. It allows users to apply specific security templates to input data to ensure it conforms to defined safety requirements before processing.

What it does

  • Sanitizes user-provided text input using specified Model Armor templates.
  • Supports processing of raw text strings or structured JSON request bodies.
  • Integrates with the gws CLI for command-line execution.
  • Accepts input directly from arguments or via standard input (stdin).

When to use it

  • When you need to sanitize user prompts before they are sent to an AI model.
  • When you have a pre-defined Model Armor template that must be applied to input data.
  • When automating security filtering workflows within a command-line environment.

Advantages

  • Enables programmatic sanitization of user input.
  • Supports flexible input methods including stdin for pipeline integration.
  • Provides a direct interface to Google Model Armor template resources.

Usage examples

“gws modelarmor +sanitize-prompt --template projects/my-project/locations/us-central1/templates/my-template --text 'Hello, how are you?'”
The provided text is sanitized using the specified Model Armor template and the result is returned.
“echo 'user input' | gws modelarmor +sanitize-prompt --template projects/my-project/locations/us-central1/templates/my-template”
The text piped from echo is processed through the Model Armor template and the sanitized output is displayed.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/googleworkspace/gws-modelarmor-sanitize-prompt/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip gws-modelarmor-sanitize-prompt.zip -d .agents/skills

Documentation by Google Workspace

modelarmor +sanitize-prompt

PREREQUISITE: Read ../gws-shared/SKILL.md for auth, global flags, and security rules. If missing, run gws generate-skills to create it.

Sanitize a user prompt through a Model Armor template

Usage

gws modelarmor +sanitize-prompt --template <NAME>

Flags

FlagRequiredDefaultDescription
--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

Files

SKILL.md

modelarmor +sanitize-prompt

PREREQUISITE: Read ../gws-shared/SKILL.md for auth, global flags, and security rules. If missing, run gws generate-skills to create it.

Sanitize a user prompt through a Model Armor template

Usage

gws modelarmor +sanitize-prompt --template <NAME>

Flags

FlagRequiredDefaultDescription
--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

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Google Workspace
Publisher
Google Workspace (Official)
Source
googleworkspace/cli · skills/gws-modelarmor-sanitize-prompt · commit cd3697e
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Google Workspace or Google Workspace.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download gws-modelarmor-sanitize-prompt.zip