paperJune 2026Unreviewed

Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systems

Kuncan Wang, Ziting Wang, Peizhuo Lv, Haoyang Li, Guoliang Li, Gao Cong, Wei Dong

Abstract

Data agents integrate LLM-driven reasoning with relational data access, executable analytical tools, and multi-step workflow orchestration, making them increasingly central to enterprise analytics. This integration introduces new security vulnerabilities across data resources, database execution, and agent reasoning, recombining concerns from database security and general-purpose LLM-agent security into failure modes that neither line of work captures on its own. To address this gap, we present

Cite

@misc{wang2026data,
  title = {{Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systems}},
  author = {Kuncan Wang and Ziting Wang and Peizhuo Lv and Haoyang Li and Guoliang Li and Gao Cong and Wei Dong},
  year = {2026},
  month = jun,
  eprint = {2606.08661},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.08661}
}