Attacker exploits SGLang flaw to breach NEAR AI inference server, takes data on about 100 users and 18 AI agents

NEAR AI said in a November 9 incident report that an unauthorized party exploited a remote code execution flaw in SGLang, the open-source inference engine on its servers, ran code on one inference server, and then reached an internal system behind the deprecated Private Chat, downloading email addresses, names and some plan and balance details for about 100 users ^[1][2]. The attacker also accessed 18 legacy AI agents that did not run in its confidential computing (TEE) environment and took chat history, settings and logs; two cloud customers’ API keys exposed in logs were revoked, and requests processed on that server on November 8, including confidential-mode requests, may also have been visible ^[1]. NEAR AI users should follow the steps in any notice from security@near.ai and treat unsolicited messages about their account or balance with caution ^[1].

Industries mainly affected: Technology

1. Users contacted by security@near.ai should follow the steps in that message .