1 🚀 产品观察 Ars Technica 2026-07-01 💬 New attack provides one more reason why AI browsers are a bad idea AI浏览器新漏洞被曝光，通过“催眠”式提示绕过安全护栏，引发对AI风险的重磅警示 Telling an LLM that 2 + 2 = 5 is enough to make it follow forbidden instructions. ai安全 浏览器漏洞 心理操纵提示 ai监管 安全护栏