Journal of Information Security Reserach ›› 2026, Vol. 12 ›› Issue (11): 1069-1077.DOI: 10.12379/j.issn.2096-1057.2026.11.11
Qian Hanwei, Ma Zhuo, Xia Lingling, Guan Junqi, Wang Qun
Published:2026-11-11
钱汉伟,马卓,夏玲玲,管钧琦,王群
CLC Number:
Qian Hanwei, Ma Zhuo, Xia Lingling, Guan Junqi, Wang Qun. The Impact of Description-Behavior Inconsistency on Tool-Calling Safety in LLM Agents[J]. Journal of Information Security Reserach, 2026, 12(11): 1069-1077.
Add to citation manager EndNote|Ris|BibTeX
URL: http://www.sicris.cn/EN/10.12379/j.issn.2096-1057.2026.11.11
| [1] OWASP Foundation. MCP03:2025 tool poisoning[EB/OL]. [2026-07-12]. https://owasp.org/www-project-mcp-top-10/2025/MCP03-2025-Tool-Poisoning. [2] Sneh J, Yan R, Yu J, et al. ToolTweak: an attack on tool selection in LLM-based agents[PP/OL]. arXiv(2025-10-02)[2026-10-13]. https://arxiv.org/abs/2510.02554. [3] Blankenstein T, Yu J, Li Z, et al. BiasBusters: uncovering and mitigating tool selection bias in large language models[PP/OL]. arXiv(2025-10-01)[2026-10-13]. https://arxiv.org/abs/2510.00307. [4] Faghih K, Wang W, Cheng Y, et al. Tool preferences in agentic LLMs are unreliable[PP/OL]. arXiv(2025-05-23)[2026-10-13]. https://arxiv.org/abs/2505.18135. [5] Yeon J, Chaudhary I, Singh G. Quantitative certification of agentic tool selection[PP/OL]. arXiv(2025-10-05)[2026-10-13]. https://arxiv.org/abs/2510.03992. [6] Greshake K, Abdelnabi S, Mishra S, et al. Not what you‘ve signed up for: compromising real-world LLM-integrated applications with indirect prompt injection[C]//Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security. New York: ACM, 2023: 79-90. [7] Zhang H, Huang J, Mei K, et al. Agent security bench (ASB): formalizing and benchmarking attacks and defenses in LLM-based agents[PP/OL]. arXiv(2024-10-03)[2026-10-13]. https://arxiv.org/abs/2410.02644. [8] Zharmagambetov A, Guo C, Evtimov I, et al. AgentDAM: privacy leakage evaluation for autonomous web agents[PP/OL]. arXiv(2025-03-13)[2026-10-13]. https://arxiv.org/abs/2503.09780. [9] El Yagoubi F, Al Mallah R, Badu-Marfo G. AgentLeak: a full-stack benchmark for privacy leakage in multi-agent LLM systems[PP/OL]. arXiv(2026-02-15)[2026-10-13]. https://arxiv.org/abs/2602.11510. [10] Baek H, Noh J, Seo S, et al. An evaluation of data leakage risks in tool-using LLM agents in realistic scenarios[PP/OL]. arXiv(2026-06-17)[2026-10-13]. https://arxiv.org/abs/2606.17114. [11] Wang H, Poskitt C M, Sun J. AgentSpec: customizable runtime enforcement for safe and reliable LLM agents[PP/OL]. arXiv(2025-03-24)[2026-10-13]. https://arxiv.org/abs/2503.18666. [12] Wang H, Poskitt C M, Wei J, et al. ProbGuard: proactive runtime monitoring for LLM agent safety via probabilistic prediction[PP/OL]. arXiv(2025-08-01)[2026-10-13]. https://arxiv.org/abs/2508.00500. [13] Yao S, Zhao J, Yu D, et al. ReAct: synergizing reasoning and acting in language models[C]//Proceedings of the 11th International Conference on Learning Representations. Kigali: OpenReview.net, 2023: 1-33. [14] Schick T, Dwivedi-Yu J, Dessi R, et al. Toolformer: language models can teach themselves to use tools[C]//Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023. Red Hook, NY: Curran Associates, Inc., 2023: 1-26. [15] Software Theorem. DBI-Bench: description-behavior inconsistency benchmark[EB/OL]. [2026-09-06]. https://github.com/software-theorem/DBI-Bench. [16] Model Context Protocol. Reference servers[EB/OL]. [2026-07-12]. https://github.com/modelcontextprotocol/servers. [17] ExecuteAutomation. MCP database server[EB/OL]. [2026-07-12]. https://github.com/executeautomation/mcp-database-server. |
| [1] | Hu Lina, Lü Xin. Research on the Path Construction for Effect Evaluation of Artificial Intelligence Integrated Development [J]. Journal of Information Security Reserach, 2026, 12(10): 879-884. |
| [2] | Hu Chengchun, Bi Yu. Progress Challenges and International Cooperation in Artificial Intelligence Safety Standardization [J]. Journal of Information Security Reserach, 2026, 12(10): 885-891. |
| [3] | Sun Qi, Li Yang. Research on the Security Mechanism of Large Language Model [J]. Journal of Information Security Reserach, 2026, 12(10): 892-898. |
| [4] | Sun Dawei, Ye Yunling. AI Safety Governance: International Experiences and Implications for China [J]. Journal of Information Security Reserach, 2026, 12(10): 899-904. |
| [5] | Du Pengfei, Li Pengfei, Jiang Jing. Research on the Security Challenges and Countermeasures of Data Element Circulation in the Context of Artificial Intelligence [J]. Journal of Information Security Reserach, 2026, 12(10): 905-910. |
| [6] | Hao Jiajie. Overlapping Risk and Compliance Thinking of Generative Artificial Intelligence Personal Information Processing [J]. Journal of Information Security Reserach, 2026, 12(10): 911-922. |
| [7] | Zhou Li, Shen Min. Technology Transition and Risk Regulation of Administrative Algorithm Decision Driven by Large Model Integration Architecture [J]. Journal of Information Security Reserach, 2026, 12(10): 923-929. |
| [8] | Luo Entao, Wang Juncheng, Bao Hongguang, Peng Tao, Liu Qin, Wu Chuyu. Response and Disposal Mechanism for Emerging Intellectual Property Risks Caused by Misuse of Large Model Technologies [J]. Journal of Information Security Reserach, 2026, 12(10): 930-937. |
| [9] | Chen Xuanheng, Zhang Zichen, Chen Qiuyang, Yu Le, Chen Wei, Liu Tingting. LLM-Assisted Privacy Risk Analysis for Internet of Vehicles Devices [J]. Journal of Information Security Reserach, 2026, 12(10): 938-947. |
| [10] | Chen Liangchen, He Boshu, Jiang Zilong, Jiang Zhengwei, Lu Zhigang, Liu Baoxu. An IoT Intrusion Detection Method Based on Adaptive Feature Optimization and Boundary-Balanced Sampling [J]. Journal of Information Security Reserach, 2026, 12(10): 948-957. |
| [11] | Yang Fangping, Nie Lixia, Li Binghui. A Dual-Modal Dynamic Feature Fusion Detection Method for Smart Contract Vulnerabilities Oriented to Lightweight Deployment [J]. Journal of Information Security Reserach, 2026, 12(10): 958-963. |
| [12] | Feng Yan, Wei Lian , Wang Xiaoqiang, Zhang Yiming, Du Xiaojian, Gao Chaohang. Application of Collaborative Signature in E-Government Services [J]. Journal of Information Security Reserach, 2026, 12(10): 964-971. |
| [13] | . [J]. Journal of Information Security Reserach, 2026, 12(E1): 2-5. |
| [14] | . [J]. Journal of Information Security Reserach, 2026, 12(E1): 6-9. |
| [15] | . [J]. Journal of Information Security Reserach, 2026, 12(E1): 10-13. |
| Viewed | ||||||
|
Full text |
|
|||||
|
Abstract |
|
|||||