Labsco
googleworkspace logo

gws-modelarmor-sanitize-prompt

✓ Official★ 29,400

by Google · part of googleworkspace/cli

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

🔥🔥✓ VerifiedFreeQuick setup
#git#maps#security
🧰 Not standalone. This skill ships with googleworkspace/cli and only works together with that tool — install the tool first, then add this skill.

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

Inspect the full instructions your agent will receiveExpand

This is the exact playbook injected into your agent when the skill activates — shown here so you can audit it before installing. You don't need to read it to use the skill.

by Google

Google Model Armor: Sanitize a user prompt through a Model Armor template. npx skills add https://github.com/googleworkspace/cli --skill gws-modelarmor-sanitize-prompt Download ZIPGitHub29.4k

modelarmor +sanitize-prompt

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

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

Copy & paste — that's it
gws modelarmor +sanitize-prompt --template projects/P/locations/L/templates/T --text 'user input'
echo 'prompt' | gws modelarmor +sanitize-prompt --template ...

Tips

  • If neither --text nor --json is given, reads from stdin.

  • For outbound safety, use +sanitize-response instead.

See Also