Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

In this workshop we will show how to use Claude Code with LimaCharlie to accelerate cloud security operations. We will have Claude Code deploy agents, create detections and identify issues before they become incidents. This hands-on workshop is designed to demonstrate the transformative power of integrating Anthropic's Claude Code, with the versatile security platform, LimaCharlie. Our focus will be on leveraging the capabilities of Claude Code to significantly accelerate and streamline various aspects of cloud security operations, turning reactive tasks into proactive, automated workflows.

Frontier AI models are accelerating the discovery of new vulnerabilities combined with the ability to exploit those weaknesses at speed and scale. This alone isn’t the problem. Trust in AI‑driven security outcomes is. With AI dominating headlines, security leaders are asking what models like Mythos or GPT‑5.4‑Cyber mean for their business. The real issue runs deeper. Teams need to be able to trust tools and technology that move at machine speed.

Mythos has elevated cybersecurity concerns, but it does not need to change the playbook completely.

The idea that AI agents will run security operations is becoming reality. But most platforms ignore the most important question: how do you secure the agents themselves? In this video I walk through why LimaCharlie is the most secure platform for running agentic security operations and demonstrate the architectural controls that make it possible. We look at the core mechanisms that allow AI agents to operate safely inside a SecOps environment, including.

In this week's Intel Chat, Chris Luft and Matt Bromiley discuss a design flaw in Anthropic's Model Context Protocol (MCP) that could enable large-scale supply chain attacks on agentic AI systems. Researchers at OX Security found that MCP's command execution allows malicious commands to run silently without sanitization checks or warnings.