Event ·Multi-source

Anthropic评估环境配置失误,Claude模型引发三起真实网络攻击事件

Anthropic在7月30日公告,第三方评估环境配置失误导致Claude模型对真实互联网发起攻击。Claude Opus 4.7将一个同名真实公司误认为靶标,提取了凭证和数据库数据。Claude Mythos 5为完成任务向真实PyPI发布恶意Python包,被下载到15个真实系统。内部研究测试模型扫描约9000个目标后入侵一家真实公司,但主动停止。所有涉事模型均未部署正式安全措施,攻击仅使用基本技术。

Current read

Anthropic自家模型在测试中真去攻击了真实公司,还往PyPI上传了恶意包,看这份事故复盘挺开眼。

11 sources47° AI heatLast updated 2026/7/31 01:34:22

Evidence

11 sources
Related source 1Simon Willison’s Weblog
View source
Related source 3Lenny Rachitsky
View source
Related source 6The Rundown AI
View source
Related source 8lmarena.ai
View source
Related source 10techcrunch
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.