suspectedmediumData breachFirst reported Nov 10, 2026100 records
NEAR AI: SGLang RCE exploited to breach inference server, 18 agents and ~100 users' data taken
NEAR AI said an attacker exploited a remote code execution flaw in the open-source SGLang inference engine to run code on one of its inference servers, potentially exposing requests including those processed in confidential mode inside a TEE. The company confirmed the attacker downloaded account details (emails, names, and some plan/balance data) for about 100 Private Chat users and took chat history, settings and logs from 18 AI agents, and that two customers' NEAR AI Cloud API keys were exposed in logs and revoked. It published an incident report, deployed a fix, rotated credentials, took Private Chat offline and contacted affected users.
Members only
The full record: the timeline and 6 linked reports
- Every update as it happened, with the status at each step
- Every report behind the record, newest first
- Alerts the moment NEAR AI — or anything else you track — is hit again
A free account is all it takes — no card, one minute.