< BACK TO NEWS
negativeSYS.SOURCE: The Hacker News• 2026-11-11T00:49:39+05:30

SGLang Remote Code Execution Vulnerability Exploited in NEAR AI Breach

A remote code execution vulnerability in SGLang was exploited to breach NEAR AI's inference server, granting access to confidential requests processed in a trusted execution environment. The incident exposed data from 18 agents and approximately 100 users.

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

Read original article

*** END OF TRANSMISSION ***