I Gave My AI Agent the Keys to My Inbox — Then Tried to Break Into It Myself
中文摘要
作者构建了AI邮件代理并进行红队测试。尽管模型成功识别了所有攻击，但仍遇到了抓取器挂起的技术问题。
English Summary
The author built an AI email agent and performed red-teaming. While the model identified all attacks, it encountered issues with a hung fetcher.
Original Excerpt
I built an AI email agent for holiday cover, then red-teamed it myself. The model flagged every attack it saw — but a hung fetcher Continue reading on Medium »