Gws Modelarmor Sanitize Prompt
googleworkspace/cliGoogle Model Armor helps you clean up user input before it reaches your AI models. This skill lets you sanitize a user prompt by running it through a Model Armor template. You can provide text directly, send a full JSON request, or pipe content from another command.
Keeping user prompts safe is important for security and content moderation. This tool filters out harmful or unwanted content automatically. Developers and system administrators can use it to protect applications from unsafe inputs.
For outgoing safety checks, there is a separate skill called sanitize-response. Use the right one depending on where the content is flowing.
Add Gws Modelarmor Sanitize Prompt skill to your workflow
Global
mkdir -p ~/.claude/skills/gws-modelarmor-sanitize-promptProject
mkdir -p .claude/skills/gws-modelarmor-sanitize-promptSource Repository
More Security Claude Code Skills
Azure Compliancemicrosoft/azure-skills
Audit Azure compliance and Key Vault expiration with azqr scans
Firebase Security Rules Auditorfirebase/agent-skills
Find weak spots in Firestore rules and get clear fixes
Golang Securitysamber/cc-skills-golang
Find and fix security flaws in Go code using expert guidance and automated tools
Clerk Nextjs Patternsclerk/skills
Secure your Next.js app with Clerk middleware, server actions, and caching
Persona It Admingoogleworkspace/cli
Keep your digital workspace safe with IT admin security workflows
Two Factor Authentication Best Practicesbetter-auth/skills
Secure user logins with two-factor authentication using Better Auth
Gws Modelarmor Create Templategoogleworkspace/cli
Create new templates for Google Model Armor to protect AI apps from harmful content
Gws Modelarmor Sanitize Responsegoogleworkspace/cli
Sanitize AI model responses for outbound safety with Model Armor