Index of every page on this site: llms.txt
All skills
googleworkspace avatar

/gws-modelarmor-sanitize-response

@cd3697e
by Google Workspacegoogleworkspace/cli32k stars
1,997
Run it yourself

Google Model Armor: Sanitize a model response through a Model Armor template.

Use this Skill: https://skilld.dev/gh/googleworkspace/cli/gws-modelarmor-sanitize-response

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈28 tokens for metadata: the name and description. ≈284 when used: this file.

Description uses 1.4% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈112 characters, or 1.4%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

modelarmor +sanitize-response

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

Sanitize a model response through a Model Armor template

Usage

gws modelarmor +sanitize-response --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-response --template projects/P/locations/L/templates/T --text 'model output'
model_cmd | gws modelarmor +sanitize-response --template ...

Tips

  • Use for outbound safety (model -> user).
  • For inbound safety (user -> model), use +sanitize-prompt.

See Also

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning2mo5 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    No security issues were detected. The skill defines a command configuration to sanitize model responses using Google Model Armor through the gws CLI tool.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

  • Runlayer8mo

    1/1 file flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at cd3697e. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 weeks ago.

Activeupdated 8 months ago
Other metadata
metadata
{
  "version": "0.22.5",
  "openclaw": {
    "category": "security",
    "requires": {
      "bins": [
        "gws"
      ]
    },
    "cliHelp": "gws modelarmor +sanitize-response --help"
  }
}
  • Security
  • CLI
  • google-workspace
  • model-armor
  • safety
  • sanitization
  • gws

README badge

README badge for googleworkspace/cli/gws-modelarmor-sanitize-response

Sanitizes model responses through Google Cloud's Model Armor templates, filtering outbound content for safety before delivery to users. Works with the gws CLI and requires a pre-configured Model Armor template resource.

Generated from the current SKILL.md.

What is Model Armor and what does this skill do?
Model Armor is Google Workspace's content safety system. This skill sanitizes model-generated responses through a Model Armor template before sending them to users.
Do I need authentication set up?
Yes. You must configure Google Workspace auth as described in gws-shared/SKILL.md before using this skill.
What's the difference between sanitize-response and sanitize-prompt?
sanitize-response filters outbound model output for safety (model to user). sanitize-prompt filters inbound user input before it reaches the model.
How do I specify which template to use?
Use the --template flag with the full resource name in the format projects/PROJECT/locations/LOCATION/templates/TEMPLATE.

Generated from the current SKILL.md. These answers refresh after source changes.