FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments

TL;DR

FinVault introduces a comprehensive benchmark to evaluate the security of financial agents powered by large language models, revealing significant vulnerabilities and the limited effectiveness of current safety measures in real-world financial scenarios.

Contribution

This work presents the first execution-grounded security benchmark for financial agents, including diverse scenarios, vulnerabilities, and test cases to evaluate safety in realistic operational environments.

Findings

Existing defenses are largely ineffective against attacks.

Attack success rates can reach up to 50% on state-of-the-art models.

Current safety measures have limited transferability in financial contexts.

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 https://github.com/aifinlab/FinVault.