Overview

AI agent security studies how tool use, memory, delegation, and interaction with people or environments create risks beyond those of a standalone language model, including prompt injection, privilege misuse, data leakage, and unsafe actions. Researchers test these risks with red-teaming and execution-grounded benchmarks for coding, browsing, GUI, embodied, and multi-agent tasks, measuring whether harmful effects occur across trajectories rather than judging text alone. Defenses range from input and memory provenance checks to sandboxing, least-privilege permissions, stateful runtime authorization, action verification, and cryptographic identity or audit mechanisms. An open challenge is making controls robust to adaptive, long-horizon attacks and interactions between tools or agents while preserving useful task completion; benchmark realism and comparable measures remain uneven.

Latest papers

CardsList

563 papers61 papers in the last four weeks, down 18% on the four weeks before. 0.5% of all new papers.

  1. Formal Analysis and Supply Chain Security for Agentic AI Skills

    Feb 27, 2026Varun Pratap BhardwajAI Agent SecurityAgent Skill Security Auditing

  2. Adversarial Intent is a Latent Variable: Stateful Trust Inference for Securing Multimodal Agentic RAG

    Feb 24, 2026Inderjeet Singh, Vikas Pahuja, Aishvariya Priya Rathina Sabapathy +8AI Agent SecurityRAG Security

  3. "Are You Sure?": An Empirical Study of Human Perception Vulnerability in LLM-Driven Agentic Systems

    Feb 24, 2026Xinfeng Li, Shenyu Dai, Kelong Zheng +4AI Agent SecurityCybersecurity

  4. AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs

    Feb 24, 2026Che Wang, Jiaming Zhang, Ziqi Zhang +6Indirect Prompt InjectionPrompt Injection Attacks

  5. ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction

    Feb 24, 2026Che Wang, Fuyao Zhang, Jiaming Zhang +6Prompt Injection DefenseAI Agent Security

  6. Agents of Chaos

    Feb 23, 2026Natalie Shapira, Chris Wendler, Avery Yen +35AI Agent SecurityLLM Agent Security

  7. Automating Agent Hijacking via Structural Template Injection

    Feb 18, 2026Xinhao Deng, Jiaqing Wu, Miao Chen +3AI Agent SecurityPrompt Injection Attacks on AI Agents

  8. From Tool Orchestration to Code Execution: A Study of MCP Design Choices

    Feb 17, 2026Yuval Felendler, Parth A. Gandhi, Idan Habler +2LLM Agent OrchestrationMCP Security

  9. A Trajectory-Based Safety Audit of Clawdbot (OpenClaw)

    Feb 16, 2026Tianyu Chen, Dongrui Liu, Xia Hu +2AI Agent SecurityAI Agent Safety

  10. Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense

    Feb 9, 2026Jiacheng Liu, Yaxin Luo, Jiacheng Cui +3CybersecurityAI Agent Security

  11. StepShield: When, Not Whether to Intervene on Rogue Agents

    Jan 29, 2026Gloria Felicia, Zitha Sasindran, Jinfeng He +3LLM GuardrailsAI Agent Security

  12. Mind the Gap: Action Rebinding Attacks against Android GUI Agents

    Jan 18, 2026Yi Qian, Kunwei Qian, Xingbang He +7Mobile GUI AutomationAdversarial Attacks

  13. MiniScope: Authorizing Agents with Least-Privilege Permissions

    Dec 11, 2025Jinhao Zhu, Xiao Huang, Kevin Tseng +4Tool Access Control for LLM AgentsAI Agent Security

  14. A Survey on Agentic Security: Applications, Threats and Defenses

    Oct 7, 2025Asif Shahriar, Md Nafiu Rahman, Sadif Ahmed +2AI Agent SecurityAutonomous Cyber Defense

  15. Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks

    Oct 1, 2025Shoumik Saha, Jifan Chen, Sam Mayers +3AI Coding AgentsAI Agent Security

  16. Enabling Regulatory Multi-Agent Collaboration: Architecture, Challenges, and Solutions

    Sep 11, 2025Qinnan Hu, Yuntao Wang, Yuan Gao +3Agent ReliabilityAI Agent Security

  17. Web3 x AI Agents: Landscape, Integrations, and Foundational Challenges

    Aug 4, 2025Yiming Shen, Jiashuo Zhang, Zhenzhe Shao +5AI Agent ReliabilityAI Agent Governance

  18. Superplatforms are Strategically Compelled to Counteract AI Agents

    May 23, 2025Jianghao Lin, Jiachen Zhu, Zheli Zhou +4AI Agent Security