A Security Analysis of Long-Horizon Agentic AI Systems: Threats, Evaluation, and Framework Development

Computer Science > Cryptography and Security [Submitted on 12 Jun 2026] A Security Analysis of Long-Horizon Agentic AI Systems: Threats, Evaluation, and Framework Development Ahmed Mohammed Almalki, Mehedi Masud This paper presents a structured analysis of security challenges in long-horizon agentic AI systems. The study reviews existing threats, evaluation approaches, attack propagation mechanisms, and security frameworks. A taxonomy of security threats and a framework for analyzing attack propagation are proposed to support future research in agentic AI security Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2606.14816 [cs.CR]   (or arXiv:2606.14816v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.14816 Focus to learn more Submission history From: Mehedi Masud Dr [view email] [v1] Fri, 12 Jun 2026 10:39:49 UTC (3,113 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)