This presentation delves into the security challenges associated with Large Language Models (LLMs) implementations, and AI Engineering in general, drawing insights from the HackAPrompt paper “Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition” (Sander Schulhoff et al.). Exploring a set of attack vectors, and demonstrating how these vulnerabilities can be exploited. Subsequently, we will discuss security measures, frameworks, and services within the Python ecosystem designed to mitigate such threats. The session will feature practical examples illustrating both the execution of these attacks and the implementation of corresponding security measures, equipping attendees with a comprehensive understanding of safeguarding LLM applications.