CyberSunil

CyberSunil/LLMVault

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.

9 good first / help-wanted issues · Python · last activity Sep 17, 2026

316 stars 75 forks 316 watchers Python MIT License
agent-security ai-security ai-security-tool artificial-intelligence ctf docker genai large-language-models llm llm-security llm-security-testing owasp owasp-llm-top-10 penetration-testing prompt-injection prompt-injection-llm-security python rag red-team vulnerable-lab
View on GitHub
9 Open Issues Need Help Last updated: Sep 17, 2026

Open Issues Need Help

View All on GitHub
Docker container runs as root 11 days ago
help wanted good first issue
CyberSunil/LLMVault
316

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.

Python
#agent-security#ai-security#ai-security-tool#artificial-intelligence#ctf#docker#genai#large-language-models#llm#llm-security#llm-security-testing#owasp#owasp-llm-top-10#penetration-testing#prompt-injection#prompt-injection-llm-security#python#rag#red-team#vulnerable-lab
No security headers set on any response [Not a Priority for Now] 19 days ago
bug good first issue
CyberSunil/LLMVault
316

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.

Python
#agent-security#ai-security#ai-security-tool#artificial-intelligence#ctf#docker#genai#large-language-models#llm#llm-security#llm-security-testing#owasp#owasp-llm-top-10#penetration-testing#prompt-injection#prompt-injection-llm-security#python#rag#red-team#vulnerable-lab
No brute-force protection on /api/submit endpoint 24 days ago
bug good first issue security
CyberSunil/LLMVault
316

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.

Python
#agent-security#ai-security#ai-security-tool#artificial-intelligence#ctf#docker#genai#large-language-models#llm#llm-security#llm-security-testing#owasp#owasp-llm-top-10#penetration-testing#prompt-injection#prompt-injection-llm-security#python#rag#red-team#vulnerable-lab
Verify the player name is escaped before it reaches the SVG card 27 days ago
help wanted good first issue priority
CyberSunil/LLMVault
316

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.

Python
#agent-security#ai-security#ai-security-tool#artificial-intelligence#ctf#docker#genai#large-language-models#llm#llm-security#llm-security-testing#owasp#owasp-llm-top-10#penetration-testing#prompt-injection#prompt-injection-llm-security#python#rag#red-team#vulnerable-lab
save_progress() rewrites the whole file on every request 30 days ago
help wanted good first issue
CyberSunil/LLMVault
316

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.

Python
#agent-security#ai-security#ai-security-tool#artificial-intelligence#ctf#docker#genai#large-language-models#llm#llm-security#llm-security-testing#owasp#owasp-llm-top-10#penetration-testing#prompt-injection#prompt-injection-llm-security#python#rag#red-team#vulnerable-lab
No rate limiting on /api/unlock-expert about 1 month ago
help wanted good first issue
CyberSunil/LLMVault
316

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.

Python
#agent-security#ai-security#ai-security-tool#artificial-intelligence#ctf#docker#genai#large-language-models#llm#llm-security#llm-security-testing#owasp#owasp-llm-top-10#penetration-testing#prompt-injection#prompt-injection-llm-security#python#rag#red-team#vulnerable-lab
File handles left open in expert_vault.py about 1 month ago
help wanted good first issue
CyberSunil/LLMVault
316

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.

Python
#agent-security#ai-security#ai-security-tool#artificial-intelligence#ctf#docker#genai#large-language-models#llm#llm-security#llm-security-testing#owasp#owasp-llm-top-10#penetration-testing#prompt-injection#prompt-injection-llm-security#python#rag#red-team#vulnerable-lab
expert_count() swallows all exceptions about 1 month ago
bug good first issue
CyberSunil/LLMVault
316

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.

Python
#agent-security#ai-security#ai-security-tool#artificial-intelligence#ctf#docker#genai#large-language-models#llm#llm-security#llm-security-testing#owasp#owasp-llm-top-10#penetration-testing#prompt-injection#prompt-injection-llm-security#python#rag#red-team#vulnerable-lab
verify() uses == instead of a constant-time comparison about 1 month ago
help wanted good first issue
CyberSunil/LLMVault
316

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.

Python
#agent-security#ai-security#ai-security-tool#artificial-intelligence#ctf#docker#genai#large-language-models#llm#llm-security#llm-security-testing#owasp#owasp-llm-top-10#penetration-testing#prompt-injection#prompt-injection-llm-security#python#rag#red-team#vulnerable-lab