AI Penetration Testing Lab Covering 9 OWASP LLM Vulnerability Categories
CybersecurityPenetration TestingAI SecurityOWASPLLMCTFPrompt InjectionSecurity Training
The lab offers nine modules with eight browser-based CTF-style challenges, each addressing a specific OWASP LLM vulnerability category. Topics include direct and indirect prompt injection, system prompt extraction, tool abuse, data exfiltration, guardrail bypass, insecure output handling, and RAG poisoning. Each module provides a concept overview, walkthrough, live attack target, and defense patterns, with the first challenge accessible without signup. The lab is available at wraith.sh/academy.