cs.AIAug 24, 2026

Concepts for Securing Agentic AI Coding and the Terok Environment

Authors: Jiří Vyskočil, Franz Pöschel, Andreas Knüpfer

Organizations: Center for Advanced Systems Understanding (CASUS) in Görlitz/Saxony/Germany

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.

Figures & tables

Figure 1: Overview about the risks (left) that apply to the five scopes (right) and which of Terok’s primary safeguards address them.
Figure 2: Overview of Terok’s software components and how they interact
Figure 3: Screenshot of Terok’s text user interface (TUI) for managing projects and tasks. The projects panel (left) shows multiple projects and the details of one of them. The tasks panel (right) shows one task belonging to the selected project.
Figure 4: Screenshot of Terok’s text user interface (TUI) with the shortcut commands to call one AI agent from a selection of providers.
More in this topic

AI Coding Agents

AI coding agents use language models and software tools to plan, edit, test, and maintain code with varying levels of autonomy.

See all 329 papers

Explore similar work

CardsList

  1. IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests

    Jul 22, 2026Ankur Singh, Jinqiu Yang, Tse-Hsun ChenAI Coding AgentsAI Agent Security

    Concordia University Montr´eal, Canada

  2. MATRA: Modeling the Attack Surface of Agentic AI Systems -- OpenClaw Case Study

    May 11, 2026Tim Van hamme, Thomas Vissers, Javier Carnerero-Cano +4AI Risk ManagementAI Agent Security

    DistriNet, KU Leuven, 3001 Leuven, Belgium · IBM Research · CISPA Helmholtz Center for Information Security +2

  3. Agentic Security: A Systematization of Tools, Failure Modes, and Design Laws for LLM-Driven Penetration Testing

    Aug 16, 2026Israt Moyeen Noumi, Tarannum Ahmed Nowshin, Md. Mehedi Hasan Nipu +3LLM Agent SecurityAutomated Penetration Testing

    Department of Computer Science and Engineering, Ahsanullah University of Science and Technology, Dhaka, Bangladesh · Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh · Department of Electrical and Computer Engineering, North South University, Dhaka, Bangladesh +3