OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage

Akshat Naik, Jay J Culligan, Yarin Gal, Philip Torr, Rahaf Aljundi, Alasdair Paren, Adel BibiSubmission to ICLR 2026 · Desk rejected

Abstract

As Large Language Model (LLM) agents become more capable, their coordinated use in the form of multi-agent systems is on the rise. Prior work has examined the safety and misuse risks associated with agents. However, much of this has focused on the single-agent case and/or setups that lack basic engineering safeguards such as access control, revealing a scarcity of threat modeling in multi-agent systems. We investigate the security vulnerabilities of a popular industry multi-agent pattern known as the orchestrator setup, in which a central agent decomposes and delegates tasks to specialized agents. Through red-teaming a concrete setup representative of industry use, we demonstrate a novel attack vector, OMNI-LEAK, that compromises several agents to leak sensitive data through a single indirect prompt injection, even in the *presence of data access control*. We report the susceptibility of frontier models to different categories of attacks, finding that both reasoning and non-reasoning models are vulnerable, even when the attacker lacks insider knowledge of the implementation details. Our work highlights the failure of safety research to generalize from single-agent to multi-agent settings, indicating the serious risks of real-world privacy breaches and financial loss.
BibTeX
@misc{naik2026omni,
  author = {Akshat Naik and Jay J Culligan and Yarin Gal and Philip Torr and Rahaf Aljundi and Alasdair Paren and Adel Bibi},
  title = {{OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage}},
  year = {2026},
  eprint = {2602.13477},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.13477},
}
Figure