gws-modelarmor-sanitize-promptlisted

This skill should be used when the user says "sanitize a user prompt", "screen input for harmful content", "filter a user message before sending to AI", "run prompt through Model Armor", "check this input for safety", or wants to sanitize inbound user input through a Model Armor template. Covers text and JSON request bodies, and stdin input.
radesjardins/RAD-Claude-Skills · ★ 3 · AI & Automation · score 77

Install: claude install-skill radesjardins/RAD-Claude-Skills

# 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 ```bash gws modelarmor +sanitize-prompt --template <NAME> ``` ## 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 ```bash 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 - [gws-shared](../gws-shared/SKILL.md) — Global flags and auth - [gws-modelarmor](../gws-modelarmor/SKILL.md) — All filter user-generated content for safety commands