LLM Agent Security

LLM: Large Language Model

Overview

The field examines how agents can be manipulated through indirect prompt injection, malicious tools or skills, poisoned memory, excessive permissions, and multi-agent interactions, sometimes leading to data leaks or harmful actions. Researchers evaluate these risks with red-team attacks and benchmarks that track agent trajectories, tool calls, and real effects—not just final answers. Defenses include runtime authorization and least privilege, sandboxing, provenance and information-flow controls, monitoring, and security-focused training. A central challenge is protecting agents over long, changing workflows without blocking legitimate tasks, while making evaluations realistic enough to capture adaptive attacks and deployment risks.

Latest papers

CardsList

351 papers27 papers in the last four weeks, down 44% on the four weeks before. 0.2% of all new papers.

  1. Only as Safe as the Weakest Agent: A Break That Appears Only When the System Is Multi-Agent

    Nov 12, 2026Keegan Wang, Anantika MannbyLLM Agent SafetyLLM Agent Security

  2. OverServe: Resource Amplification Attacks on SaaS Agents via Tool--Prompt Co-Design

    Nov 10, 2026Ruiheng Yu, Oteo Mamo, Siyu Gan +2LLM Agent SecurityTool-Augmented Language Model Agents

  3. Comparative Analysis of Agent Evaluation Frameworks: Stability, Detection, and Discovery in Enterprise Analytics Agents

    Nov 10, 2026Howard Zhang, Chuck Arvin, Logan Brown +3LLM Agent EvaluationLLM Agent Reliability

  4. Harness Matters: Measuring and Dissecting Security Resilience in Web Agents

    Nov 9, 2026Xinyi Wu, Jiagui Chen, JiaYi Dong +5LLM Agent SecurityLLM Agent Harnesses

  5. ShadowBench-MCP: Measuring Shadow Invocations in MCP-Style Tool Routing

    Nov 9, 2026Eyhab Al-Masri, Wenjun YangLLM Agent SecurityLLM Routing

  6. LatentTriad: Pre-Action Risk Representations for Malicious Agent Skill Detection

    Nov 3, 2026Zhe Yu, Yi Liu, Ying Zhang +1LLM Agent SecurityAgent Skill Security Auditing

  7. RuntimeTickets: Source-Grounded Security Obligations for Agent Skills

    Nov 2, 2026Kuiyi Gao, Xue Liu, Bowei HeLLM Agent SecurityRuntime Enforcement for AI Agents

  8. Cumulative and Audited Guardrail Tool Evolution for LLM Agent Safety

    Nov 2, 2026Xiao Yang, Aishan Liu, Siyuan Liang +5AI Agent SecurityLLM Agent Security

  9. Beyond Prompt Injection: The Tool Update Gap in LLM Agent Security

    Nov 1, 2026Shiyu Kan, Yue Qi, Yufei Han +3LLM Agent Security

  10. How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces

    Oct 30, 2026Donghang Duan, Qingyu Liu, Yifei Liu +3User Attribute Inference AttacksLLM Agent Security

  11. What Standard Evaluations Hide About Detectors of Hijacked LLM Agents: Rare Attacks, Unseen Tools and Benchmark Transfer

    Oct 30, 2026Mahmoud Abbasi, Juan M. Núñez V., Amin ShahrakiLLM Agent SecurityAI Agent Monitoring

  12. Characterizing LLM Agent Behaviors in Module Shadowing Environments

    Oct 29, 2026Shuai Yang, Enmeng Lu, Jinyu Fan +7LLM Agent SecurityAI Agent Auditing

  13. Scan Before You Install: Detecting and Mitigating Local and Composite Vulnerabilities in Skills

    Oct 27, 2026Parth A. Gandhi, Avital Aviv, Prasanna N. Wudali +2Agent Skill Security AuditingSoftware Vulnerability Detection

  14. CoSA: The Conflict of Skills Attack in Real-World LLM Agent Ecosystems

    Oct 26, 2026Yujia Zheng, Tianhao Li, Shangzhi Xu +6LLM Agent SecurityLLM Agent Safety

  15. ProbeID: Verifying MCP Tool Identity for LLM Agents under Registry Drift

    Oct 24, 2026Guanxing Chen, Sining Zhang, Haohuai He +3LLM Agent VerificationAI Agent Security

  16. Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems

    Oct 21, 2026Daniel Ruiz, Luca Luceri, Emilio FerraraLLM Agent SecurityPrivacy Leakage in Language Models

  17. Disclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent Memory

    Oct 20, 2026Masahiro Kaneko, Hiromi Arai, Timothy BaldwinLLM Agent SecurityPrivacy Protection for LLM Agents

  18. The Show-Up Attack: When Subagents Win Over Their Supervisor

    Oct 20, 2026Maosen Zhang, Jianshuo Dong, Yutong Zhang +3LLM Agent SecurityMulti-Agent System Security

  19. PROVISO: Provenance-Informed Action Selection for Secure LLM Agents

    Oct 19, 2026Bo Yan, Qi Zhang, Ziwen Kan +2LLM Agent SecurityLLM Agents

  20. SPIDES: Information-Flow Control for Browser Agents

    Oct 16, 2026Egor Zverev, Juhee Kim, Leon Trampert +4LLM Agent SecurityInformation Flow Control