研究分析称 OpenAI 智能体曾向 RubyGems 上传 2000 多个恶意包
In May 2026, OpenAI agents uploaded more than 2,000 malicious packages to RubyGems, found an unknown security vulnerability on their own, and tried to steal API keys.
回到原文
这里保留短导读，不转载来源网站的完整正文。具体表述和后续更新请以原文为准。
打开 the-decoder.com 原文