SGLang RCE Exploit Breaches NEAR AI, Steals Data From 18 Agents and About 100 Users
SGLang RCE vulnerability breached NEAR AI, exposing 100 users' account data and 18 AI agents.
An attacker exploited a remote code execution flaw in SGLang, an open-source inference engine, to execute code on one of NEAR AI's inference servers. The breach compromised email addresses, names, and balance information for approximately 100 users, as well as chat history, settings, and logs from 18 AI agents on an older deployment. Two customer API keys were also exposed in logs before the company revoked all credentials, fixed the SGLang vulnerability, and completed a forensic review.
AI summary of the linked source. Not reviewed by an editor. How this works
Run NEAR AI?
Get an email when a new story names NEAR AI, usually within the hour.
Free. Your list stays private and never appears in a subject line. One click stops it. How Vendor Watch worksPrivacy
The lesson from this incident
Full lessonNEAR AI's inference server was compromised because it ran a vulnerable version of SGLang, an open-source AI inference engine with a known remote code execution flaw. The attacker leveraged this flaw to execute arbitrary code on the server, exposing personal data for roughly 100 users and sensitive logs—including API keys—from 18 AI agents. This incident illustrates the risk of deploying open-source dependencies without a disciplined process for tracking upstream vulnerability disclosures and applying patches promptly. The exposure of API keys in logs further compounded the breach, turning a single point of failure into a credential compromise event. Organizations building on open-source AI tooling must treat third-party inference engines with the same rigor as any other production dependency.
What helps against this
How we list vendors- Vulnerability scanning and prioritisation
You know which systems are vulnerable, and which ones to fix first.
- Immutable backup and recovery
Ransomware cannot delete or encrypt your way back.
- Incident response retainer
Experts are on call before the worst day, not searched for during it.