activity
20242026
collaborators
Showing cs.CRShow all

7 papers · 1 filter

cs.CR2026

CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills

Mingxiao Liu, Zhoumian Jiang, Jianan Ma +4

Autonomous AI agents tackling Long Horizon Tasks depend on marketplace skills that are certified one at a time: a scanner returns a safety verdict for each skill and declares the e…

cs.CR2026

When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems

Jialuo Chen, Lingqi Jiang, Xinhao Deng +7

Self-evolving skill (SES) systems distill agent trajectories into persistent skills, allowing untrusted experience to become trusted instruction. We introduce PoisonedEvolution, a…

cs.CR2026

Piggybacking on Perception: Stealthy Concurrent Audio Prompt Injections against Multimodal LLM Agents

Mingxiao Liu, Yitong Li, Haoren Zhao +6

Large Language Model (LLM)-driven multimodal agents are increasingly deployed to execute autonomous tasks via continuous audio interaction. While this paradigm enhances interaction…

cs.CR2026

Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies

Ruixiao Lin, Xinhao Deng, Qingming Li +12

Self-evolving LLM agent systems, which autonomously update their model parameters, memory, tools, and architectures, introduce a qualitatively new threat landscape in which adversa…

cs.CR2026

ASEval: Automated Trajectory-Level Security Testing for Autonomous Agents

Jianan Ma, Xiaohu Du, Ruixiao Lin +9

As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Existing L…

cs.CR2026

Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats

Xinhao Deng, Yixiang Zhang, Jiaqing Wu +15

Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled…