智能体工作流

gws-modelarmor-sanitize-prompt

Name: gws-modelarmor-sanitize-prompt
Author: googleworkspace

googleworkspace/cli

Google Model Armor: Sanitize a user prompt through a Model Armor template.

安装命令

$ npx skills add https://github.com/googleworkspace/cli --skill gws-modelarmor-sanitize-prompt

要点

Sanitize user prompts through Google Model Armor safety templates.

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

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

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

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)