Most data science and tech teams are not aware of the potential security vulnerabilities when building AI-powered applications utilizing self-hosted Large Language Models (LLMs). One of the more practical techniques to secure these AI-powered applications involves building a vulnerability scanner that checks for common vulnerabilities such as prompt injection. In this session, the speakers will use Python to build a custom scanner to help teams identify and mitigate security issues specific to their self-hosted LLMs right away. They will also take a look at various strategies on how to mitigate the vulnerabilities found by our scanner.