← 返回事件
持续讨论AI

DeepSeek-Reasonix: How a poisoned config can hijack an AI coding agent

图:GitLab Blog

发生了什么

GitLab's Threat Research Group found a flaw, ConfigPoisoning, that runs attacker code when a developer views a file's diff in DeepSeek-Reasonix.

摘要按规则整理自下方来源原文

为什么在扩散

来源