Jun 2026
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
SafeClawArena is developed, a benchmark of 406 adversarial tasks executed in containerized replicas of real agent platforms with canary-marked credentials and evaluated via automated taint tracking across nine output channels, exposing the inadequacy of current defenses and suggesting directions for future hardening.
Peizhi Niu, Wenjie Qu, Shangding Gu et al.
· arXiv.org · 2 citations