Concepts for Securing Agentic AI Coding and the Terok Environment
2026-08-24 • Artificial Intelligence
Artificial IntelligenceSoftware Engineering
AI summaryⓘ
The authors discuss a new type of AI called agentic AI that helps with software development and is more advanced than earlier AI tools. They explain that while this technology is promising, it also brings serious IT security risks, some of which are worse than before. The authors assess these risks, propose ways to reduce them without losing the benefits, and describe how they implemented their ideas. Their work aims to help others use agentic AI safely while exploring its potential. They acknowledge that this is an ongoing effort in a rapidly changing field.
Agentic AISoftware DevelopmentIT Security RisksLarge Language Models (LLMs)AI-Assisted CodingRisk MitigationSoftware SecurityAI SafetyImplementation Overview
Authors
Jiří Vyskočil, Franz Pöschel, Andreas Knüpfer
Abstract
Agentic AI is a fascinating new tool for software development. It is a huge step forward compared to "conventional" AI assisted coding, which in turn was a considerable breakthrough earlier. AI support through LLMs is a young and very fast-moving field. The "conventional" (non-agentic) flavor became useful and productive in early 2025 (around 18 months ago) and the agentic flavor followed in fall 2025 (approximately 9 months ago). Besides all its benefits and potential, it also carries some fundamental risks for IT security. And the agentic approach added very severe risks while making others much more dangerous. With all the motivation to explore this fascinating new tool we should not ignore the risks but actively address them. We present (I) an assessment of the IT security risks, (II) a concept for mitigating them without breaking its benefits, and (III) an overview about an implementation of our concept. In this very dynamic field this is likely not the final and once-and-for-all answer to the identified issues but still a substantial step forward in responsible usage of Agentic AI for software development. It should also be a contribution to the community to allow early and eager evaluation of the potential of agentic AI for software development without actually suffering from its implied IT security risks.