DOI: 10.69554/jhix5712 ISSN: 2398-5119

A formal model of agentic AI vulnerabilities in containerised cloud environments

Advait Patel, Vaishnavi Gudur, Charit Upadhyay, Shalini Sudarsan
Show PDF Cite
In today’s evolving digital landscape, a new kind of AI has emerged: agentic artificial intelligence (AI) systems. These are not just tools but intelligent entities that act on their own, make decisions, and carry out tasks proactively. Once placed inside containerised cloud environments such as Kubernetes, however, these powerful agents open the door to a whole new category of security concerns. They often interact on the fly with application programming interfaces, data channels, and other AI agents, sometimes all at once, and not always in predictable ways. Recognising the risks, this paper introduces a formal framework designed to capture and analyse these unique vulnerabilities. Going beyond theory, the study offers a full threat taxonomy focused on agent behaviours, uses temporal logic to trace how agents and environments interact over time, and introduces a practical measure called the Agentic Vulnerability Exposure Metric (AVEM). To put this model to the test, researchers ran simulated cyberattacks on a Kubernetes-based orchestration system that was managing large language model (LLM)-powered agents. The results were eye-opening: AVEM was able to expose security holes such as weak isolation between agents, overlooked permissions, and routes for privilege escalation that had gone undetected before. To test the practicality of the model, real-world attack scenarios are simulated on a Kubernetes-managed AI platform utilising LLM agents. The findings reveal that AVEM effectively uncovers weaknesses such as poorly defined isolation boundaries, unexpected capabilities, and opportunities for privilege escalation between agents. This article is also included in The Business & Management Collection which can be accessed at https://hstalks.com/business/.

More from our Archive