Tool-Flow Taint Analysis for Data Exfiltration Defense in Large Language Model Agents
DOI:
https://doi.org/10.66857/jirt.v3i2.52Keywords:
Autonomous Agents, Taint Analysis, Data Exfiltration, Cybersecurity, Large Language ModelsAbstract
The rapid integration of Large Language Models into autonomous agentic systems has introduced unprecedented capabilities for task automation, reasoning, and tool utilization. However, equipping these agents with the ability to access external APIs, internal databases, and arbitrary web resources significantly broadens the attack surface for data exfiltration. Malicious actors can leverage prompt injection and indirect prompt injection techniques to hijack the agent control flow, forcing it to retrieve sensitive information and transmit it to attacker-controlled destinations. Existing security mechanisms, which predominantly rely on static prompt filtering or heuristic anomaly detection, fail to maintain context across complex, multi-step tool invocations. This paper introduces a comprehensive framework based on Tool-Flow Taint Analysis designed to mitigate data exfiltration in Large Language Model agents. By adapting classical dynamic taint analysis principles to the semantic and operational workflows of agent toolchains, the proposed architecture tracks sensitive data from predefined sources through intermediate natural language reasoning steps to potential external sinks. We establish robust semantic taint propagation rules capable of operating within the non-deterministic environment of Large Language Models. Extensive experimental evaluations demonstrate that the proposed system achieves high efficacy in intercepting exfiltration attempts while maintaining a low false-positive rate and negligible latency overhead. The findings provide a critical foundation for securing next-generation autonomous agents against sophisticated data-stealing attacks in enterprise environments.
References
[1] Zhang, Y., Zhang, Y., Zhao, M., Feng, S., & Cheung, Y. M. (2026). How to Ask the AI: A User Perspective Survey for Large Language Model Prompting.IEEE Transactions on Artificial Intelligence.
[2] Luo, P., & Ding, X. (2026). C-MAPPO-TSC: A Collaborative Multi-Agent Reinforcement Learning Framework for Urban Traffic Signal Control and Congestion Mitigation. Fundamental Scientific Reports in Multidisciplinary Areas, 2 (02), 170-181.
[3] Yang, Z., Liang, B., & Ji, W. (2021). An intelligent end–edge–cloud architecture for visual IoT-assisted healthcare systems. IEEE internet of things journal, 8(23), 16779-16786.
[4] Liao, Qiuyue, et al. "Explainable Artificial Intelligence for 5G Security and Privacy: Trust, Governance, and Resilience." (2025).
[5] Tao, J., Lyu, R., & Cao, X. (2026). A Scalable Data Governance Architecture for Privacy-Aware Intelligent Learning Systems in Lifelong. Future-Adaptive Intelligence and Lifelong Systems, 1 (1).
[6] Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017). Membership inference attacks against machine learning models. In Proceedings of the IEEE Symposium on Security and Privacy.
[7] Qu, D., Ma, Y., & Wang, Y. (2026). STR-GNN: stability-regularized graph neural networks for suppressing spurious temporal variations in dynamic community detection. Scientific Reports.
[8] Liu, C., Zhang, J., Zhang, T., Wang, Y., Zhou, H., & Jin, Q. (2026). HRIBench: Benchmarking Interaction-Centric Human-Robot Collaboration.arXiv preprint arXiv:2607.13056.
[9] Zhao, Q., & Huang, Y. (2026). DAREA: A Dynamic AI-Driven Architecture for Real Estate Asset Tokenization on Blockchain.Fundamental Scientific Reports in Multidisciplinary Areas,2(02), 182-192.
[10] Hu, X., Wan, Z., & Murthy, N. N. (2019). Dynamic pricing of limited inventories with product returns. Manufacturing & Service Operations Management, 21(3), 501-518.
[11] Yang, Z., Ji, W., & Wang, Z. (2024). Adaptive joint configuration optimization for collaborative inference in edge-cloud systems. Science China Information Sciences, 67(4), 149103.
[12] Wang, S., Zhang, X., Wang, P., & Li, X. (2026). Design of Magnetic Sensor Array-Based PUFs for IoT Security. IEEE Transactions on Instrumentation and Measurement, 75, 1-9.
[13] Yao, Y., Zhao, J., Li, Z., Cheng, X., & Wu, L. (2023). Jamming and eavesdropping defense scheme based on deep reinforcement learning in autonomous vehicle networks. IEEE Transactions on Information Forensics and Security, 18, 1211-1224.
[14] Yao, Y., Shu, F., Li, Z., Cheng, X., & Wu, L. (2023). Secure transmission scheme based on joint radar and communication in mobile vehicular networks. IEEE transactions on intelligent transportation systems, 24 (9), 10027-10037.
[15] Zhang, H., Zandsalimy, M., & Sushmita, S. (2026). Exposing LLM Safety Gaps Through Mathematical Encoding: New Attacks and Systematic Analysis.arXiv preprint arXiv:2605.03441.
[16] Chen, Q. (2026, February). Construction of a Blockchain and IoT-Based Cold Chain Logistics Data Security Traceability System. In2026 International Conference on Digital Analysis and Processing, Intelligent Computation (DAPIC)(pp. 396-399). The Academy of Engineering and Education.
[17] Yang, W., Qin, Y., & Yang, Y. (2021). Characterizing the multicast nature of malicious flows in CCN via SIS epidemic model. IEEE Systems Journal, 16(2), 2240-2250.
[18] Qu, D., Ma, Y., Yan, J., & Pyrozhenko, M. (2026). TriMeta-BFNet: A Tri-Meta Stacked Atypical-Frequency Bayesian Fourier Neural Network for Hallucination-Resistant Community Detection. Mathematics, 14 (13), 2283.
[19] Tao, J., Lyu, R., & Cao, X. (2026). A Deep Learning-Based Automated Content Moderation Framework for Online Platforms.Future-Adaptive Intelligence and Lifelong Systems,1(1).
[20] Yang, Z., Ji, W., Guo, Q., & Wang, Z. (2023, October). Javp: Joint-aware video processing with edge-cloud collaboration for dnn inference. In Proceedings of the 31st ACM International Conference on Multimedia (pp. 9152-9160).
[21] Long, J., Xu, Z., Jiang, T., Yao, W., Jia, S., Ma, C., & Chen, X. (2025, April). Robust SAM: on the adversarial robustness of vision foundation models. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 6, pp. 5775-5783).
[22] Liu, Fuqiang, and Sicong Jiang. "Temporally sparse attack for fooling large language models in time series forecasting." (2025).
[23] Ma, Y., & Qu, D. (2026, February). IMFM-GNN: Interpretable Multimodel GNN Via Fourier-Markov Dynamics for Community Detection in Sustainable Energy Networks. In 2026 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) (pp. 1-6). IEEE.
[24] Yang, P., Chen, W., Wang, K., Ai, L., Yang, E., & Shi, T. (2026, July). EVM-QuestBench: An Execution-Grounded Benchmark for Natural-Language Transaction Code Generation. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)(pp. 35513-35529).
[25] Sun, Fang, et al. "Modeling Structural Deviation in 10-K Risk Factors: A Semantic Anomaly Detection and Explainable AI Approach." Risks 14.4 (2026): 87.
[26] Li, B., Zhang, R., Liang, H., Zhang, J., Zhang, J., Chen, X., ... & Wang, J. (2026). Interagent: Physics-based multi-agent command execution via diffusion on interaction graphs. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 15253-15265).
[27] Liang, R., Xu, S., Xie, C., Chen, J., Ren, F., Yang, S., & Yabe, T. (2026). Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency. Advances in Neural Information Processing Systems, 38, 99445-99471.
[28] Wuyang Zhang and Shichao Pei. 2026. Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use. arXiv:2604.05432 [cs.CR] doi:10.48550/arXiv.2604.05432
[29] Li, X., Wang, P., Li, G., & Zhang, Y. (2023). Design of a novel self-test-on-chip interface ASIC for capacitive accelerometers. IEEE Transactions on Circuits and Systems I: Regular Papers, 70(7), 2834-2843.
[30] Ma, Y., Qu, D., & Wang, Y. (2026). HALO-GNN: hallucination-resistant temporal graph neural networks for dynamic community detection.Scientific Reports.
[31] Zhang, Q., Gao, W., Liu, C., Yao, Y., Yan, S., Shu, F., & Jin, S. (2025). Covert transmission for active RIS-aided full-duplex UAV integrated sensing, communication, and computation systems. IEEE Journal on Selected Areas in Communications.
[32] Li, X., Wang, P., Li, G., Ni, L., & Zhang, Y. (2023). Design of interface circuits and lightweight PUF for TMR sensors. IEEE Sensors Journal, 23(11), 11754-11761.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Chun Tian, Hiu-Tung Li, Michelle Yu
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles in the Journal of Innovative Research and Technology are licensed under Creative Commons Attribution 4.0 (CC BY 4.0). Users can share, adapt, and build upon the material with appropriate credit, without additional restrictions.
