Skip to content
TrustedSkillsbeta
Back to all skills

Gws Modelarmor Sanitize Prompt

Checked
googleworkspace·vlatest·ai-ml·Apache-2.0

This skill sanitizes prompts used in Google Workspace AI models to mitigate potential risks and ensure safer interactions.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add googleworkspace/cli --skill gws-modelarmor-sanitize-prompt -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

googleworkspace

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned googleworkspace/cli at a3768d0e82.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
a3768d0e82
Manifest
skills/gws-modelarmor-sanitize-prompt/SKILL.md
Scanned
1 file, 46 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill sanitizes prompts before they are sent to Google AI Studio models, ensuring inputs comply with safety guidelines and preventing the injection of harmful or policy-violating content. It acts as a pre-processing filter to maintain secure interactions within your Google Workspace environment.

When to use it

  • Public-facing chatbots: Deploy customer service agents that must strictly adhere to safety policies without risking model abuse.
  • Data ingestion pipelines: Clean unstructured user inputs before processing them through generative AI workflows in Google Cloud.
  • Compliance requirements: Enforce organizational data governance rules by blocking prompts containing sensitive or prohibited information.
  • Internal tools: Secure internal knowledge assistants to prevent accidental leakage of confidential corporate data via prompt injection.

Key capabilities

  • Real-time sanitization of user inputs before model inference.
  • Integration with Google AI Studio models for enhanced safety filtering.
  • Prevention of malicious or policy-violating prompt injections.
  • Deployment via the googleworkspace/cli toolset.

Example prompts

  • "How do I install the gws-modelarmor-sanitize-prompt skill to secure my chatbot?"
  • "What happens when a user submits a harmful prompt to an agent using this sanitization layer?"
  • "Can I configure the sanitize-prompt skill to block specific keywords before they reach Google AI Studio?"

Tips & gotchas

Ensure your Google Workspace account has access to Google AI Studio features, as this skill relies on that integration for effective filtering. While highly effective at blocking obvious violations, complex adversarial attacks may still require additional monitoring layers beyond basic sanitization.