Keep your Claude Code setup safe from hidden risks. This tool scans your configuration files for security problems. It checks CLAUDE.md, settings.json, and more. It looks for secrets, dangerous permissions, and injection attacks. Use it when you start a new project or change your setup. It helps you find and fix issues fast.
AgentShield powers this scan. You run it with simple commands in your terminal. It gives you a clear report with a grade from A to F. You can even auto-fix some problems. This makes your AI coding environment much more secure.
Global
mkdir -p ~/.claude/skills/security-scanProject
mkdir -p .claude/skills/security-scanSource Repository
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 Promptgoogleworkspace/cli
Clean user prompts safely with Google Model Armor templates