modelarmor▌

Sanitize user prompts through Google Model Armor safety templates. \n \n Requires a Model Armor template resource name and accepts text input via flag, stdin, or full JSON request body \n Designed for inbound prompt safety; use the companion +sanitize-response command for outbound response filtering \n Integrates with Google Cloud authentication and global flags defined in gws-shared \n

Sanitize model responses through Google Model Armor templates for outbound safety. \n \n Applies Model Armor templates to filter model outputs before delivery to users \n Accepts text input via --text flag or piped stdin, with optional full JSON request body override \n Requires template resource name in format projects/PROJECT/locations/LOCATION/templates/TEMPLATE \n Complements the +sanitize-prompt command for inbound user input safety \n

Google Model Armor: Filter user-generated content for safety. \n \n Provides three core helper commands: sanitize prompts, sanitize responses, and create custom filtering templates \n Integrates with Google Workspace services via the gws CLI tool with shared authentication and security rules \n Requires schema inspection via gws schema to discover available resources, methods, and parameter requirements before executing API calls \n

Create Google Model Armor templates to filter prompts and responses for safety. \n \n Requires GCP project ID, location, and template ID; supports preset templates (jailbreak) or custom JSON configuration \n Templates work with companion sanitize-prompt and sanitize-response commands for comprehensive content filtering \n Write operation requiring user confirmation before execution \n Defaults to jailbreak preset if no preset or JSON configuration is specified \n