My name is Loïc, and I am currently a PhD student and security researcher at MBZUAI in Abu Dhabi, UAE. My research focuses on post-compromise security in AI-orchestrated infrastructures, with a particular emphasis on how attackers abuse trusted agentic systems from within enterprise environments. I am especially interested in the following question: Do agentic systems extend the living-off-the-land paradigm by exposing a new class of policy-compliant, native capabilities that attackers can exploit to move laterally, evade detection, and inherit organizational reach — without ever exploiting the agent itself?
My background spans social sciences, behavioral sciences, machine learning, and cybersecurity. These multidisciplinary academic and professional experiences allow me, as a researcher, to approach problems from different perspectives and explore unconventional ways of thinking about security challenges.
Alongside my research, I actively participate in CTF competitions and bug bounty programs (@lmshunter), with a particular focus on AI and agentic systems. If you would like to learn more, you can visit my GitHub (@lmshunter) or explore the articles below. If you would like to discuss specific topics or collaborate on research, please feel free to contact me on LinkedIn.