我给了 Claude Code 一句话:"全面信息收集渗透测试这个网站"。三个多小时后,它交给我多个漏洞联合一个完整的纯 API 验证码绕过方案(批量跑敏感信息)——包含 ECDH 密钥交换逆向、AES-GCM 加密还原、NCC 图像识别算法、以及一个能批量注册账号的全自动化脚本。中间我一次都没有打开聊天窗口。
Ask an AI coding agent to scan open-source code for security holes, and it might run the attacker's code on your own machine instead.
That is the finding in a proof-of-concept published Wednesday by the AI Now Institute, an attack it calls "Friendly Fire." It works against Anthropic's Claude Code and OpenAI's Codex when either is running in an autonomous mode that approves its own