Agent-Skills.md

Agent Skills: modelarmor +sanitize-response

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

securityID: dbmcco/claude-agent-toolkit/gws-modelarmor-sanitize-response

Repository

dbmcco/claude-agent-toolkit
dbmccoLicense: MIT
122

Install this agent skill to your local

pnpm dlx add-skill https://github.com/dbmcco/claude-agent-toolkit/tree/HEAD/skills/gws-modelarmor-sanitize-response

Skill Files

Browse the full folder contents for gws-modelarmor-sanitize-response.

Download Skill

Loading file tree…

skills/gws-modelarmor-sanitize-response/SKILL.md

Skill Metadata

Name
gws-modelarmor-sanitize-response
Description
"Google Model Armor: Sanitize a model response through a Model Armor template."

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