FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918285631553536 |
|---|---|
| author | Yang, Zhi Li, Runguo Qiang, Qiqi Wang, Jiashun Lou, Fangqi Li, Mengping Cheng, Dongpo Xu, Rui Lian, Heng Zhang, Shuo Liang, Xiaolong Huang, Xiaoming Wei, Zheng Liu, Zhaowei Guo, Xin Wang, Huacan Chen, Ronghao Zhang, Liwen |
| author_facet | Yang, Zhi Li, Runguo Qiang, Qiqi Wang, Jiashun Lou, Fangqi Li, Mengping Cheng, Dongpo Xu, Rui Lian, Heng Zhang, Shuo Liang, Xiaolong Huang, Xiaoming Wei, Zheng Liu, Zhaowei Guo, Xin Wang, Huacan Chen, Ronghao Zhang, Liwen |
| contents | 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 https://github.com/aifinlab/FinVault. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07853 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments Yang, Zhi Li, Runguo Qiang, Qiqi Wang, Jiashun Lou, Fangqi Li, Mengping Cheng, Dongpo Xu, Rui Lian, Heng Zhang, Shuo Liang, Xiaolong Huang, Xiaoming Wei, Zheng Liu, Zhaowei Guo, Xin Wang, Huacan Chen, Ronghao Zhang, Liwen Cryptography and Security Artificial Intelligence 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 https://github.com/aifinlab/FinVault. |
| title | FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2601.07853 |