AI Security Labs & CTFs
88+ hands-on practice environments for AI red teaming and prompt injection, featuring real LLM challenges with difficulty ratings from beginner to advanced
PromptTrace
Hands-on prompt injection labs with real LLMs, a Gauntlet CTF, and Context Trace showing the full prompt stack the model receives.
Gandalf
Wargame-style challenge where players must trick an LLM into revealing secret passwords across progressively harder levels.
Damn Vulnerable LLM Agent
Intentionally vulnerable AI agent designed for practicing LLM exploitation techniques.
Vulnerable MCP Servers Lab
Collection of 9 labs covering path traversal, RCE, prompt injection, and supply-chain attacks on MCP.
Splunk MCP LLM SIEMulator
Full-stack lab for generating and detecting MCP-specific attack logs using Splunk SIEM integration.
LLM CV Screener Lab
Lab demonstrating HR-agent vulnerabilities through prompt injection in resume screening systems.
DevOps Attack Surface Lab
Hands-on lab exploring pipeline security and privilege escalation vectors in CI/CD environments.
AWSGoat
Deliberately vulnerable AWS cloud infrastructure for practicing cloud security exploitation.
Know a resource we're missing?
Send us a message with the resource name and link. We review every suggestion.