On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models

Computer Science > Cryptography and Security [Submitted on 11 Aug 2026] On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models Md Jafrin Hossain, Mohammad Arif Hossain, Nirwan Ansari Large Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code execution, and maintaining persistent memory. When these agents operate with real-world privileges---calling APIs, modifying files, and querying databases---a compromised reasoning step can trigger unauthorized data access, irreversible state changes, or cascading failures, yet the security research community has not kept pace. To quantify the state of the field, we conducted a systematic literature review under PRISMA 2020 guidelines across six databases, screening 743 records and retaining 85 papers (2023--2025) on agentic LLM security. Attack research outpaces defense work by 3.9:1. Perception-layer vulnerabilities (prompt injection, jailbreaking, adversarial perturbations) dominate, accounting for 66\% of papers, while action-layer vulnerabilities (tool misuse, code injection, sandbox escape) appear in only 4.7\%, misaligned with real-world risk. Code execution security accounts for 3.5\%, and tool-augmented agents 12\%. We contribute a four-layer taxonomy mapping 13 vulnerability types across perception, brain, action, and interaction layers, and identify seven open problems centered on containment. Agentic LLM insecurity stems from architectural coupling, where weak isolation allows vulnerabilities to propagate across layers. Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2608.10530 [cs.CR]   (or arXiv:2608.10530v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2608.10530 Focus to learn more Submission history From: Mohammad Arif Hossain [view email] [v1] Tue, 11 Aug 2026 06:11:26 UTC (1,618 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-08 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?)