Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack

Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hacking, where agents maximize a score without performing the intended task, emerges spontaneously in frontier models without overfitting. We argue tha...

GLORY RBG-100 安全漏洞

GLORY RBG-100 is a cash recycling machine from the British company GLORY. There is a security vulnerability in GLORY RBG-100; this vulnerability stems from the ISPK-08 software component containing hard-coded operating system credentials, which may allow unauthorized remote access and complete...

CVE-2025-43833 WordPress Absolute Links plugin <= 1.1.1 - SQL Injection vulnerability

Improper Neutralization of Special Elements used in an SQL Command 'SQL Injection' vulnerability in Amir Helzer Absolute Links absolute-links allows Blind SQL Injection.This issue affects Absolute Links: from n/a through = 1.1.1...