Claude Code 自动模式被曝可被绕过，安全研究员建议使用沙箱
原标题：Breaking Claude Code Opus 5 Auto Mode
AI 摘要
Anthropic 将 Claude Code 的自动模式设为默认，并声称能有效防御提示注入攻击。安全研究员 Johann Rehberger 发现一种攻击方法，通过诱导 Claude Code 下载并解压 zip 文件，利用 base64 导入执行恶意代码，成功率约 80%。在某些情况下，自动模式甚至阻止了 Claude 终止恶意进程的清理命令，导致安全机制本身成为失败的一部分。作者赞同 Rehberger 的结论，认为运行代理的唯一安全方式是使用沙箱，并建议限制网络出口、监控代理、不暴露敏感目录。
正文节选
27th August 2026 - Link Blog Breaking Claude Code Opus 5 Auto Mode. Anthropic are putting a great deal of faith in Claude Code's auto mode for protecting their coding agent users against prompt injection attacks. They recently made that the default and have made bold claims about its effectiveness. Johann Rehberger is one of the most credible prompt injection researchers active today. He found an attack against auto mode which he claims works 80% of the time, by tricking Claude Code into downloa