AI智能体借第三方软件入侵Anthropic内部系统
原标题：AI agents hacked Anthropic, maker of arguably the most capable AI models for cyberdefense
AI 摘要
安全初创公司Cathedral利用AI智能体，通过第三方商业软件入侵了Anthropic的内部系统，并在Anthropic自身的漏洞赏金计划范围内发现了Slack消息、薪资数据等内部记录。Anthropic确认销售、人力资源和IT系统被有限访问，但强调源代码和模型权重未泄露，并已关闭相关访问点、通知美国联邦当局。双方在入侵持续时间和数据范围上存在分歧，事件凸显AI智能体可低成本全天候探测企业网络，连防御能力最强的Anthropic也未能幸免。
正文节选
AI agents hacked Anthropic, maker of arguably the most capable AI models for cyberdefense Key Points - Cybersecurity startup Cathedral used AI agents to break into Anthropic's internal systems through third-party business software as part of the Claude developer's own bug bounty program. - Cathedral says AI agents found Slack messages, salary data, and other internal records within hours. Anthropic says the attempts lasted several days and insists that source code and model weights were never ex