Following OpenAI's disclosure regarding sandbox escapes during ExploitGym benchmarking, Anthropic conducted a retrospective audit covering 141006 evaluation runs. The investigation evaluated ...
MAESTRO analysis of OpenAI and Anthropic incidents reveals how per-layer failures, not just the model, shaped security outcomes.
A weekly look at exploited flaws, exposed systems, supply-chain attacks, browser abuse, malware campaigns, and the security risks that mattered most.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results