skills.rest
73ai
73aiOFFICIAL
Explore all skills by this author →
Website𝕏@73aiorgGitHub

gws-modelarmor-sanitize-response

Sanitize model responses through a Model Armor template.

4|2|Updated Feb 26, 2026
Search Tags:#template#security#ai-safety#sanitize#gws#model-output#model-armor
One-click install
npx skills add https://github.com/73ai/openbotkit --skill gws-modelarmor-sanitize-response-73ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gws-modelarmor-sanitize-response
Source: https://github.com/73ai/openbotkit/tree/main/skills/gws-modelarmor-sanitize-response
Command: npx skills add https://github.com/73ai/openbotkit --skill gws-modelarmor-sanitize-response-73ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Sanitize model responses through a Model Armor template to enforce outbound safety.

Core Features & Use Cases

  • Apply a Model Armor template to a model's output to strip or redact sensitive content.
  • Integrate with gws to validate and enforce security rules before sending content.
  • Use cases include customer-facing replies, chat completions, and automation where model outputs are exposed to users.

Quick Start

Run gws modelarmor +sanitize-response with your chosen template to sanitize the model output.

Frequently Asked Questions about gws-modelarmor-sanitize-response

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I sanitize model output before sending it to users?▼

You sanitize model output by applying a Model Armor template via the gws tool. This enforces outbound safety workflows by stripping or redacting sensitive content before sharing completions with users.

What is a Model Armor template used for in AI safety workflows?▼

A Model Armor template defines security rules to validate and redact sensitive content in AI-generated responses. It enforces outbound safety compliance for chat completions and customer-facing automation workflows.

Do I need the gws tool to redact sensitive content from chat completions?▼

Yes, the gws tool is required to execute the sanitize-response action. It interfaces with your Model Armor template to validate and strip sensitive content from model outputs before delivery.

Can I input text or JSON to sanitize AI model responses?▼

Yes, you can pass AI model responses to the sanitizer using either the --text or --json input flags. This allows the Model Armor template to process and redact various outbound response formats.

When should I apply outbound safety templates to model-generated content?▼

Apply outbound safety templates when exposing model responses to users in customer-facing replies or automation. This ensures compliance by validating and redacting content before it leaves your system.

Related Skills

Explore More Software Engineering Skills→
haberlahhaberlah
8

gws-modelarmor-sanitize-response

Sanitize model responses through a Model Armor template using the gws CLI.

Community
Intermediate
clawpod-appclawpod-app
46

draft-response

Draft professional customer-facing responses for support channels with tone adaptation.

Community
Advanced
jiyangnanjiyangnan
2

skill-guard

Scan ClawHub skills for vulnerabilities and malicious code before installation.

Community
Advanced
latchagentlatchagent
2

enclave-ingress-filter

Filter sensitive content from HTTP responses using regex patterns.

Official
Advanced