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.

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
6 Open Issues Need Help Last updated: Sep 17, 2026

Open Issues Need Help

View All on GitHub
No rate limiting on /api/unlock-expert 3 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
Verify the player name is escaped before it reaches the SVG card 3 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 3 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
File handles left open in expert_vault.py 3 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
expert_count() swallows all exceptions 3 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
verify() uses == instead of a constant-time comparison 3 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