Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming

Recent computer-using-agent CUA red-teaming papers report prompt-injection attack success rates ASR of 42-98%, but these headline numbers cluster on retired models and on the most-vulnerable model in each paper's panel. We ask whether those techniques, reproduced as hand-crafted templates, still...

Jenkins lambdatest-automation Plugin missing permission check

Jenkins lambdatest-automation Plugin 1.20.9 and earlier does not perform a permission check in an HTTP endpoint. This allows attackers with Overall/Read permission to enumerate credentials IDs of LAMBDATEST credentials stored in Jenkins. Those can be used as part of an attack to capture the...