Adversarial Attacks in Multi-Agent LLM Pipelines: Unveiling Structural Vulnerabilities in Agentic AI Architectures

Computer Science > Cryptography and Security [Submitted on 1 Aug 2026] Adversarial Attacks in Multi-Agent LLM Pipelines: Unveiling Structural Vulnerabilities in Agentic AI Architectures Faisal Haque Bappy, Tahrim Hossain, Tarannum Shaila Zaman, Raiful Hasan, Kamrul Hasan, Tariqul Islam Multi-agent LLM pipelines orchestrate multiple specialized language model agents into structured workflows where intermediate outputs are passed across agents to solve complex tasks. This design introduces a security gap absent in single-agent settings: once an agent accepts adversarial content, it is propagated as trusted input throughout the pipeline. We argue that this vulnerability stems from the absence of boundary verification, a security primitive that enforces explicit validation of data as it crosses inter-agent boundaries, including content, identity, execution intent, and state integrity. Without such verification, modern pipelines embed implicit trust assumptions that are not adversarially robust, giving rise to structurally distinct attack surfaces (e.g., content injection, agent impersonation, plan deviation, and memory poisoning). Leveraging annotated production traces from the GAIA and SWE-Bench benchmark, we show that these vulnerabilities arise in benign deployments and largely evade existing evaluation frameworks. We further operationalize these failure modes within a controlled multi-agent setting and evaluate them across GPT-5-mini, Claude Sonnet 4.5, and Kimi K2.5 under identical pipeline configurations. The results reveal that attack success aligns with pipeline structure rather than model capability, indicating that adversarial vulnerability is fundamentally an architectural property and motivating a shift toward pipeline-level defenses. Comments: This paper has been accepted at the 2026 IEEE Global Communications Conference (GLOBECOM) Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) Cite as: arXiv:2608.00718 [cs.CR]   (or arXiv:2608.00718v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2608.00718 Focus to learn more Submission history From: Faisal Haque Bappy [view email] [v1] Sat, 1 Aug 2026 15:35:58 UTC (1,378 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 cs.MA 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?)