Category: AI

The edge isn't the AI model, but how you assemble the system around it. We built a custom agentic harness that structures vulnerability research into distinct stages, from codebase exploration and analysis to validation and exploitation. Applied to FreeRDP, the workflow found vulnerabilities that could be chained into remote code execution, with a human researcher validating the findings and guiding the process along the way.

During a Red Team exercise we were able to chain multiple LLM and web-based vulnerabilities to achieve admin account takeover from a low-privileged account. Trusting the LLM turned out to be the first falling domino of a long chain of events that lead to complete compromise. In this article we describe how it went down.

Agentic AI gives LLMs the power to act: query databases, call APIs or access files. But when your tools blindly trust the LLM, you've created a confused deputy. Here's a practical and comprehensive approach to understanding and identifying this critical authorization flaw.