Our institution has launched an innovative collaboration between our generative AI solution and a student-led cybersecurity club, setting new standards for AI security testing and student engagement in real-world challenges. Key aspects: Unique partnership: Students access pre-release code in staging environments Comprehensive testing methods: Input boundaries, system prompt extraction, web application security, LLM, jailbreaking Focus on AI-specific vulnerabilities: Exploring unique risks posed by AI systems Educational impact: Hands-on experience in penetration testing for students Real-world application: Balancing learning with actual system testing The project will be formalized in a penetration test report. This is a model for institutions to address emerging technological challenges while providing learning opportunities. It demonstrates how we can proactively secure AI systems while cultivating the next generation of cybersecurity leaders.