Cover Image

Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mo, Kanghua, Hu, Li, Long, Yucheng, Li, Zhihao
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary
by: Wang, Hongru, et al.
Published: (2025)

ToolTweak: An Attack on Tool Selection in LLM-based Agents
by: Sneh, Jonathan, et al.
Published: (2025)

MalTool: Malicious Tool Attacks on LLM Agents
by: Hu, Yuepeng, et al.
Published: (2026)

"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills
by: Liu, Yi, et al.
Published: (2026)

CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks
by: Zhang, Xu, et al.
Published: (2025)

Are Tools All We Need? Unveiling the Tool-Use Tax in LLM Agents
by: Zhang, Kaituo, et al.
Published: (2026)

Automated Standardization of Legacy Biomedical Metadata Using an Ontology-Constrained LLM Agent
by: Hardi, Josef, et al.
Published: (2026)

EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions
by: Wu, Xiaorui, et al.
Published: (2025)

AgentEscapeBench: Evaluating Out-of-Domain Tool-Grounded Reasoning in LLM Agents
by: Guo, Zhengkang, et al.
Published: (2026)

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
by: Ning, Liang-bo, et al.
Published: (2025)

Who's the Mole? Modeling and Detecting Intention-Hiding Malicious Agents in LLM-Based Multi-Agent Systems
by: Xie, Yizhe, et al.
Published: (2025)

TADDLE: A Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews
by: Duan, Hanqi, et al.
Published: (2026)

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents?
by: Li, Xinzhe, et al.
Published: (2026)

Insider Attacks in Multi-Agent LLM Consensus Systems
by: Sun, Xiaolin, et al.
Published: (2026)

AutoBackdoor: Automating Backdoor Attacks via LLM Agents
by: Li, Yige, et al.
Published: (2025)

CP-Guard: Malicious Agent Detection and Defense in Collaborative Bird's Eye View Perception
by: Hu, Senkang, et al.
Published: (2024)

Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use
by: Guo, Ruocheng, et al.
Published: (2026)

Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts
by: Wang, Boxuan, et al.
Published: (2026)

Targeted Bit-Flip Attacks on LLM-Based Agents
by: Wang, Jialai, et al.
Published: (2026)

AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks
by: Jiang, Tanqiu, et al.
Published: (2026)

AutoTool: Efficient Tool Selection for Large Language Model Agents
by: Jia, Jingyi, et al.
Published: (2025)

Targeting the Core: A Simple and Effective Method to Attack RAG-based Agents via Direct LLM Manipulation
by: Li, Xuying, et al.
Published: (2024)

Counterfactual Trace Auditing of LLM Agent Skills
by: Zhou, Xiaolin, et al.
Published: (2026)

Reproducibility Study of Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation
by: Garcia, Jose L., et al.
Published: (2025)

Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs
by: Yang, Haoming, et al.
Published: (2025)

BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents
by: Feng, Yunhao, et al.
Published: (2026)

UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents
by: Liang, Yijuan, et al.
Published: (2026)

FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use
by: Lu, Jiaxuan, et al.
Published: (2026)

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks
by: Li, Ang, et al.
Published: (2025)

AgentOrchestra: Orchestrating Multi-Agent Intelligence with the Tool-Environment-Agent(TEA) Protocol
by: Zhang, Wentao, et al.
Published: (2025)

EvoTool: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection
by: Yang, Shuo, et al.
Published: (2026)

INFA-Guard: Mitigating Malicious Propagation via Infection-Aware Safeguarding in LLM-Based Multi-Agent Systems
by: Zhou, Yijin, et al.
Published: (2026)

Hallucinating AI Hijacking Attack: Large Language Models and Malicious Code Recommenders
by: Noever, David, et al.
Published: (2024)

Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System
by: Jiang, Ziyou, et al.
Published: (2025)

Utility-Guided Agent Orchestration for Efficient LLM Tool Use
by: Liu, Boyan, et al.
Published: (2026)

How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities
by: Mo, Lingbo, et al.
Published: (2023)

Hidden in the Metadata: Stealth Poisoning Attacks on Multimodal Retrieval-Augmented Generation
by: Edemacu, Kennedy, et al.
Published: (2026)

Small LLMs Are Weak Tool Learners: A Multi-LLM Agent
by: Shen, Weizhou, et al.
Published: (2024)

MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents
by: Zhang, Dongsen, et al.
Published: (2025)

Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate
by: Qi, Senmao, et al.
Published: (2025)