OpenSkillIndex← back to search
claude-codesecurity

Cli gws-modelarmor-sanitize-prompt

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

install
source · Clone the upstream repo
git clone https://github.com/googleworkspace/cli
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/googleworkspace/cli "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/gws-modelarmor-sanitize-prompt" ~/.claude/skills/googleworkspace-cli-gws-modelarmor-sanitize-prompt && rm -rf "$T"
manifest: skills/gws-modelarmor-sanitize-prompt/SKILL.md
tags
#security#prompt-engineering#google-model-armor#content-filtering#api-integration
source content

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

Usage

gws modelarmor +sanitize-prompt --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-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