Ai Scanner Garak
aradotso/trending-skillsAn AI model safety scanner helps you find weaknesses in your language models. It runs 179 security probes across 35 vulnerability families. These tests cover the OWASP LLM Top 10 risks. You can scan any AI that works through an API or a browser chat interface.
This tool gives you clear results like the Attack Success Rate. You can schedule scans to run automatically. Export reports as PDF or send them to a SIEM system. It is built on the open source NVIDIA garak library.
Anyone who builds or uses AI models can benefit. Developers, security teams, and compliance officers use it to check for prompt injection, data leakage, and other threats. The setup is simple with Docker and a few environment variables.
Add Ai Scanner Garak skill to your workflow
Global
mkdir -p ~/.claude/skills/ai-scanner-garakProject
mkdir -p .claude/skills/ai-scanner-garakSource 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
Firestore Security Rules Auditorfirebase/agent-skills
Audit your Firestore security rules and get a detailed vulnerability score from 1 to 5
Skill Vetteruseai-pro/openclaw-skills-security
Manual skill vetting with security checks before any install
Two Factor Authentication Best Practicesbetter-auth/skills
Secure user logins with two-factor authentication using Better Auth
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