Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

In this video, we explore the growing security risk of prompt injection in large language model (LLM) applications. As AI becomes embedded in more products, new vulnerabilities emerge, especially through natural language manipulation. We break down how LLMs work, the importance of system prompts, and demonstrate five real-world prompt injection techniques used to extract sensitive information or bypass safeguards. You’ll see live examples using different models and learn why newer models are more resilient, but still not immune.

Supply chain attacks targeting AI have recently been making headlines — and keeping the CrowdStrike OverWatch team busy. Jared Myers, director of CrowdStrike OverWatch, joins Adam in this episode to discuss his team’s approach to detecting and responding to these attacks.

What looks like a simple coding task can quickly turn into a real cyberattack. In this demo, we show how a modern malware-free attack works step by step. It starts with something that feels completely normal: a job interview and a small coding assignment. No suspicious files. No obvious malware. But once the script is executed, everything changes. You’ll see how adversaries use trusted tools like Git, Notepad, and Python to gain access, establish command and control, and move inside an environment without being detected at first.

Sisense powers analytics experiences inside the applications businesses rely on every day. As an API-first platform, securing those connections is critical, especially as AI agents increasingly operate through APIs to access data and trigger workflows. In this conversation, Sangram, CISO and VP of IT at Sisense, and Michael Callahan, CMO at Salt Security, discuss how Sisense approached API security strategically to protect their platform, maintain customer trust, and support innovation in the Agentic AI era.