paperJune 2026Unreviewed

The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety Requirements

Md Jafrin Hossain, Mohammad Arif Hossain, Weiqi Liu, Nirwan Ansari

Abstract

Agentic large language model systems that autonomously invoke tools, maintain persistent memory, and execute multi-step plans are increasingly deployed in public-facing domains, including government services, healthcare triage, and financial advising. We ask whether the frameworks used to build these systems provide architectural-level structural safety guarantees. Applying six containment principles derived from a compositional model of agentic architectures, we audit three dominant frameworks

Cite

@misc{hossain2026containment,
  title = {{The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety Requirements}},
  author = {Md Jafrin Hossain and Mohammad Arif Hossain and Weiqi Liu and Nirwan Ansari},
  year = {2026},
  month = jun,
  eprint = {2606.12797},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.12797}
}