Preprint · 2026 · Open access

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

Akshat D. Naik, Jay Culligan, Yarin Gal, Philip Torr, Rahaf Aljundi, Alasdair Paren, Adel Bibi

arXiv (Cornell University) · Published 13 February 2026 · DOI 10.48550/arxiv.2602.13477

Open PDFView at the publisherCite this paper

In brief

“OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage” is a 2026 preprint by Akshat D. Naik and 6 co-authors, published in arXiv (Cornell University). OpenAlex counts 16 citations as of 19 November 2026. It is open access under a public domain licence: the full text is free to read at arXiv (Cornell University).

Citations
16
Most cited in
2026 (15)
References
20
Authors
7

Abstract

As Large Language Model (LLM) agents become more capable, their coordinated use in the form of multi-agent systems is anticipated to emerge as a practical paradigm. 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 missing 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 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 a likely future use case, 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 importance of safety research to generalize from single-agent to multi-agent settings, in order to reduce the serious risks of real-world privacy breaches and financial losses and overall public trust in AI agents.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Naik, A. D., Culligan, J., Gal, Y., Torr, P., Aljundi, R., Paren, A., & Bibi, A. (2026). OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.13477

MLA 9

Naik, Akshat D., et al. “OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2602.13477.

Chicago

Naik, Akshat D., Jay Culligan, Yarin Gal, Philip Torr, Rahaf Aljundi, Alasdair Paren, and Adel Bibi. 2026. “OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.13477.

Harvard

Naik, A. D. et al. (2026) ‘OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage’, arXiv (Cornell University). doi:10.48550/arxiv.2602.13477.

IEEE

A. D. Naik et al., “OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2602.13477.

BibTeX

@misc{naik2026omni,
  title     = {{OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage}},
  author    = {Naik, Akshat D. and Culligan, Jay and Gal, Yarin and Torr, Philip and Aljundi, Rahaf and Paren, Alasdair and Bibi, Adel},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2602.13477},
  url       = {https://doi.org/10.48550/arxiv.2602.13477}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning

  • multi-agent systems
  • LLM agents
  • data leakage
  • prompt injection
  • access control
  • security vulnerabilities
  • threat modeling
  • privacy violations

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Naik, A. D., Culligan, J., Gal, Y., Torr, P., Aljundi, R., Paren, A., & Bibi, A. (2026). OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.13477

How many times has this paper been cited?

16 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Akshat D. Naik, Jay Culligan, Yarin Gal, Philip Torr, Rahaf Aljundi, Alasdair Paren, Adel Bibi.

What is the DOI of this paper?

10.48550/arxiv.2602.13477, permanently at https://doi.org/10.48550/arxiv.2602.13477. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.