This paper has been withdrawn by Liwen Zhang

[Submitted on 9 Jan 2026 (v1), last revised 30 Jul 2026 (this version, v2)]

Authors:Zhi Yang, Runguo Li, Qiqi Qiang, Jiashun Wang, Fangqi Lou, Mengping Li, Dongpo Cheng, Rui Xu, Heng Lian, Shuo Zhang, Xiaolong Liang, Xiaoming Huang, Zheng Wei, Zhaowei Liu, Xin Guo, Huacan Wang, Ronghao Chen, Liwen Zhang

No PDF available, click to view other formats

Abstract:Financial agents powered by large language models (LLMs) are increasingly deployed for investment analysis, risk assessment, and automated decision-making, where their abilities to plan, invoke tools, and manipulate mutable state introduce new security risks in high-stakes and highly regulated financial environments. However, existing safety evaluations largely focus on language-model-level content compliance or abstract agent settings, failing to capture execution-grounded risks arising from real operational workflows and state-changing actions. To bridge this gap, we propose FinVault, the first execution-grounded security benchmark for financial agents, comprising 31 regulatory case-driven sandbox scenarios with state-writable databases and explicit compliance constraints, together with 107 real-world vulnerabilities and 963 test cases that systematically cover prompt injection, jailbreaking, financially adapted attacks, as well as benign inputs for false-positive evaluation. Experimental results reveal that existing defense mechanisms remain ineffective in realistic financial agent settings, with average attack success rates (ASR) still reaching up to 50.0\% on state-of-the-art models and remaining non-negligible even for the most robust systems (ASR 6.7\%), highlighting the limited transferability of current safety designs and the need for stronger financial-specific defenses. Our code can be found at this https URL.

Submission history

From: Liwen Zhang [view email]
[v1] Fri, 9 Jan 2026 03:25:45 UTC (41,819 KB)
[v2] Thu, 30 Jul 2026 04:41:28 UTC (1 KB) (withdrawn)