FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments
This addresses security vulnerabilities in high-stakes financial environments, providing a novel benchmark for evaluating agent safety, though it is incremental in extending safety evaluations to execution-grounded settings.
The paper tackles the problem of safety risks in financial agents powered by large language models by introducing FinVault, the first execution-grounded security benchmark, which reveals that existing defense mechanisms are ineffective with attack success rates up to 50.0% on state-of-the-art models and 6.7% on the most robust systems.
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.