Evaluating Frontier AI Agents As Autonomous Clinical Security Auditors

Clinical AI models can expose patients to harm when adversarial vulnerabilities go undetected, yet formal security auditing requires statistical expertise, specialized tools, and significant time. We present an open evaluation task, built on METR Task Standard v0.3.0, that tests whether frontier ...

Shescape 操作系统命令注入漏洞

shescape is an open source package of simple shell escaping programs for JavaScript. Use it to escape user-controlled input to shell commands to prevent shell injection. shescape versions 1.4.0 through 1.5.1 are vulnerable to an information disclosure vulnerability that stems from using the escap...