gws-modelarmor-sanitize-prompt

by googleworkspace32k

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

Install

The skill file stays in the publisher's repository.

Paste the copied command in a terminal. It installs this SKILL.md into that agent.

npx skills add googleworkspace/cli --skill gws-modelarmor-sanitize-prompt -a cursor -y

How do I install gws-modelarmor-sanitize-prompt?: Download skills/gws-modelarmor-sanitize-prompt/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
Where does gws-modelarmor-sanitize-prompt live?: The publisher keeps it at https://github.com/googleworkspace/cli.
Which agents can use gws-modelarmor-sanitize-prompt?: Claude, Cursor, and Codex can read a SKILL.md you add from the publisher's repository.

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)