Exposing Weak Links in Multi-Agent Systems under Adversarial Prompting

ICLR 2026 Conference Submission25240 Authors

Keywords: Multi-agent systems, Vulnerability Attacks, Security

TL;DR: We introduce SafeAgents, a framework for evaluating security vulnerabilities in multi-agent LLM systems, revealing that popular architectures contain significant security flaws stemming from design choices like autonomy levels and context sharing.

Abstract: LLM-based agents are increasingly deployed in multi-agent systems (MAS). As these systems move toward real-world applications, their security becomes paramount. Existing research largely evaluates single-agent security, leaving a critical gap in understanding the vulnerabilities introduced by multi-agent design. However, existing systems fall short due to lack of unified frameworks and metrics focusing on unique rejection modes in MAS. We present SafeAgents, a unified and extensible framework for fine-grained security assessment of MAS. SafeAgents systematically exposes how design choices such as plan construction strategies, inter-agent context sharing, and fallback behaviors affect susceptibility to adversarial prompting. We introduce DHARMA, a diagnostic measure that helps identify weak links within multi-agent pipelines. Using SafeAgents, we conduct a comprehensive study across five widely adopted multi-agent architectures (centralized, decentralized, and hybrid variants) on four datasets spanning web tasks, tool use, and code generation. Our findings reveal that common design patterns carry significant vulnerabilities. For example, centralized systems that delegate only atomic instructions to sub-agents obscure harmful objectives, reducing robustness. Our results highlight the need for security-aware design in MAS. Link to code is here https://anonymous.4open.science/r/SafeAgents/ .

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 25240