Summary from the original article

An attacker exploited a remote code execution flaw in SGLang, an open-source inference engine, and ran code on one of NEAR AI's inference servers last Sunday. The attacker could also have seen requests being processed on that server that day, including requests sent in confidential mode, the company said earlier this week. That mode processes requests inside a trusted execution environment (TEE
By info@thehackernews.com (The Hacker News) ·
AI key points, how left, center and right framed this story, tone by side and loaded language are part of News.gg Premium.
Upgrade this serverAn attacker exploited a remote code execution flaw in SGLang, an open-source inference engine, and ran code on one of NEAR AI's inference servers last Sunday. The attacker could also have seen requests being processed on that server that day, including requests sent in confidential mode, the company said earlier this week. That mode processes requests inside a trusted execution environment (TEE
Yesterday · thehackernews.com · You are reading this one