LLM-based financial agents increasingly rely on both numerical market data and textual signals for sequential trading and stock prediction. However, financial misinformation often appears as subtle textual perturbations rather than explicit falsehoods, making it difficult to detect while still capable of significantly altering agent reasoning and decisions. To study this risk, we propose AutoRedTrader, an autonomous red-teaming framework that generates finance-specific misinformation through behavioral bias manipulation, minor textual perturbations, and rewriting strategies, with agent feedback used to strengthen attacks over time. We evaluate AutoRedTrader in a POMDP-based financial agent simulation environment, and further examine a time-series-informed grounding setting for robustness analysis. The framework enables systematic evaluation of how subtle misinformation affects financial agents and whether historical market evidence can stabilize decisions under misleading textual signals. We evaluate the framework on Bitcoin transaction data. The results show that AutoRedTrader achieves the strongest attack performance with 69.00% misinformation exposure rate and 26.67% attack success rate, outperforming general-purpose misinformation and red-teaming baselines. Ablation studies further show that all modules contribute to generating retrievable and decision-effective financial misinformation.

翻译：基于大型语言模型的金融智能体日益依赖数值市场数据和文本信号进行序列化交易与股票预测。然而，金融虚假信息常表现为微妙文本扰动而非明显谬误，这种特性使其难以被检测，却能显著改变智能体的推理与决策。为研究此风险，我们提出AutoRedTrader这一自主红队测试框架，通过行为偏差操纵、轻微文本扰动及改写策略生成金融特定虚假信息，并利用智能体反馈随时间推移强化攻击效果。我们在基于POMDP的金融智能体模拟环境中评估AutoRedTrader，并进一步引入时间序列信息锚定设置进行鲁棒性分析。该框架可系统评估隐性虚假信息对金融智能体的影响，以及历史市场证据在误导性文本信号下能否稳定决策。我们在比特币交易数据上评估该框架，结果显示AutoRedTrader实现了69.00%的虚假信息暴露率与26.67%的攻击成功率，性能优于通用型虚假信息攻击与红队测试基线。消融研究进一步表明，所有模块均对生成可检索且具决策影响力的金融虚假信息有所贡献。