gws-modelarmor-sanitize-response

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

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "gws-modelarmor-sanitize-response" with this command: npx skills add googleworkspace/cli/googleworkspace-cli-gws-modelarmor-sanitize-response

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

FlagRequiredDefaultDescription
--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

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Open in GitHubOpen in ClawHub

Related Skills

Related by shared tags or category signals.

Coding

gws-gmail

No summary provided by upstream source.

Repository SourceNeeds Review
7K-googleworkspace
Coding

gws-drive

No summary provided by upstream source.

Repository SourceNeeds Review
6.8K-googleworkspace
Coding

gws-calendar

No summary provided by upstream source.

Repository SourceNeeds Review
6.5K-googleworkspace
Coding

gws-docs

No summary provided by upstream source.

Repository SourceNeeds Review
6.2K-googleworkspace