MetaMancer: Practical Tool Selection Attacks against LLM Agents
Wenbin Zhai, Yihao Liu, Dong Wang, Hao Chen, Bin Xiao
2026Year
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Your agent calls
Lunesearch_papers
Free to start. No credit card required.
Terminal
Install the CLIlune papers get 63f563cb-06a8-4742-b5df-8d006bd3437bRelated papers
- Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious ToolsKanghua Mo, Li Hu, Yucheng Long, Zhihao LiNeurIPS 2025 · 37 citations
- CVE-Genie: An LLM-Based Multi-Agent Framework for Reproducing CVEsSaad Ullah, Praneeth Balasubramanian, Wenbo Guo, Amanda Burnett et al.CCS 2026
- Prompt Injection Attack to Tool Selection in LLM AgentsJiawen Shi, Zenghui Yuan, Guiyao Tie, Pan Zhou et al.NDSS 2026 · 181 citations
- BACAgent: LLM-Powered Detection of Broken-Access-Control Vulnerabilities in Web ApplicationsFengyu Liu, Yuan Zhang, Zheng Lou, Tian Chen et al.CCS 2026
- MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI AgentsKaijie Zhu, Xianjun Yang, Jindong Wang, Wenbo Guo et al.ICML 2025
