From gws
Sanitizes user prompts using Google Model Armor safety templates via gws CLI. Reads from stdin, --text, or --json; outputs filtered content for safe model input.
How this skill is triggered — by the user, by Claude, or both
Slash command
/gws:gws-modelarmor-sanitize-promptThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> **PREREQUISITE:** Read `../gws-shared/SKILL.md` for auth, global flags, and security rules. If missing, run `gws generate-skills` to create it.
PREREQUISITE: Read
../gws-shared/SKILL.mdfor auth, global flags, and security rules. If missing, rungws generate-skillsto 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) |
gws modelarmor +sanitize-prompt --template projects/P/locations/L/templates/T --text 'user input'
echo 'prompt' | gws modelarmor +sanitize-prompt --template ...
npx claudepluginhub wadewarren/gws-claude-pluginSanitizes AI prompts and model responses for safety using Google Model Armor CLI. Supports template creation and inspection via gws modelarmor.
Deploys runtime guardrails for bidirectional prompt and response filtering in AI systems. Use when designing or reviewing AI architectures needing prompt injection protection, content filtering, or input/output safety controls.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.