Ethical Hacking News
A critical vulnerability in the SGLang open-source inference engine has exposed NEAR AI and stolen sensitive user data. The incident highlights the importance of cybersecurity and the need for robust security measures to prevent such attacks.
The SGLang open-source inference engine had a critical vulnerability that was exploited by an attacker. The attacker gained access to sensitive user data, including email addresses, names, and account information. The vulnerability allowed the attacker to run code on a NEAR AI inference server, bypassing the TEE's protection. The attacker also accessed 18 AI agents, chat history, settings, and logs, and exposed two customers' NEAR AI Cloud API keys. The company has taken steps to mitigate the breach, including revoking sessions and administrator credentials, and deploying a fix for the SGLang flaw. The incident highlights the importance of keeping software up to date and prioritizing cybersecurity in AI-powered systems.
The world of cybersecurity is constantly on high alert for vulnerabilities that could potentially expose sensitive information to malicious actors. Recently, a critical vulnerability in the SGLang open-source inference engine has come to light, and its implications are far-reaching. The vulnerability, which was exploited by an attacker, allowed the individual to run code on one of NEAR AI's inference servers, thereby gaining access to sensitive user data.
According to the company, NEAR AI, the attacker could also have seen requests being processed on that server that day, including requests sent in confidential mode. However, the TEE "does not protect against a vulnerability in the software running inside the environment," the company said. SGLang runs inside the TEE, which is how the attacker could reach requests there.
The attacker's access has since been closed, but not before the individual moved further into the company's systems. The company has confirmed that the attacker downloaded account details for about 100 users, including email addresses and names, and for some accounts, plan and balance information. It is worth noting that the company found no sign that stored Private Chat conversations or uploaded files were accessed.
Furthermore, the attacker also reached 18 AI agents on an older deployment of NEAR AI Agents that did not run inside the company's TEE. From those agents, the attacker took data including chat history, settings and logs. Two customers' NEAR AI Cloud API keys were exposed in logs. The company has revoked both.
In response to the breach, the company revoked all active sessions and administrator credentials, replaced all agent tokens and took Private Chat offline. It also deployed a fix for the SGLang flaw on all of its inference servers, rotated its remaining credentials and completed a full forensic review. Access to its NEAR AI Cloud service has been restored, and the company has contacted users whose account details or agents it confirmed were accessed.
The company has also asked users to be careful with messages about their account or balance that they did not ask for. In a follow-up post, the company said users who have not heard from it do not need to do anything. It has not said whether people whose requests passed through the affected server last Sunday were among those contacted.
The breach highlights the importance of keeping software up to date and the need for robust security measures to prevent such attacks. It also serves as a reminder that even with the best security measures in place, vulnerabilities can still arise. In this case, the vulnerability in SGLang was exploited by an attacker who was able to run code on one of NEAR AI's inference servers, thereby gaining access to sensitive user data.
The incident has also sparked concerns about the security of AI-powered systems, particularly those that rely on open-source software. As AI technology continues to advance, it is essential that we prioritize cybersecurity and take proactive measures to prevent such breaches.
In conclusion, the vulnerability in SGLang has exposed NEAR AI and stolen sensitive user data. The incident highlights the importance of cybersecurity and the need for robust security measures to prevent such attacks. As AI technology continues to advance, it is essential that we prioritize cybersecurity and take proactive measures to prevent such breaches.
Related Information:
https://www.ethicalhackingnews.com/articles/A-Critical-Vulnerability-in-SGLang-Exposes-NEAR-AI-and-Steals-Sensitive-User-Data-ehn.shtml
https://thehackernews.com/2026/11/sglang-rce-exploit-breaches-near-ai.html
Published: Tue Nov 10 16:05:26 2026 by llama3.2 3B Q4_K_M
