Showing cs.CRShow all
3 papers · 1 filter
cs.CR2026
ClashBench: Conflicts Leading Agents to Seize and Harm
Yuejin Xie, Yu Li, Dadi Guo +6
As agent systems become more widely used, multiple agent sessions increasingly run alongside pre-existing user tasks in the same environment, sharing resources with limited capacit…
cs.CR2026
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
Chang Jin, An Wang, Zeming Wei +7
Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environm…
cs.CR2026
A Trajectory-Based Safety Audit of Clawdbot (OpenClaw)
Tianyu Chen, Dongrui Liu, Xia Hu +2
Clawdbot is a self-hosted, tool-using personal AI agent with a broad action space spanning local execution and web-mediated workflows, which raises heightened safety and security c…