3 papers
cs.CR2026
Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents
Xiaofang Yang, Ziqi Miao, Dianbo Sui +2
Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable channel for steering future actions…
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…