Lucene search
K

The vulnerability of artificial intelligence servers for applications based on large language models like BricksLLM arises from the failure to protect the SQL query structure when processing the parameter customId. This allows attackers to access protected information or execute arbitrary code.

🗓️ 27 Apr 2026 00:00:00Reported by FSTEC of Russia — Information Security Threat DatabaseType 
bdu_fstec
 bdu_fstec
🔗 bdu.fstec.ru👁 2 Views

BricksLLM vulnerability: customId SQL query unprotected, enabling data access or arbitrary code.

Data

Build on a solid foundation with Vulners data

We provide the essential building blocks for cybersecurity solutions with comprehensive, structured, and constantly updated vulnerability and exploits data

Api

Power your application with Vulners API

The Vulners REST API offers reliable, high-performance access to vulnerability intelligence, with 99.9% SLA uptime and CDN-backed data delivery for seamless global access

App

Assess and manage vulnerabilities with Vulners tools

Built on top of Vulners' database and SDK, end-user solutions give security professionals and developers lightweight and powerful tools for vulnerability remediation

21 May 2026 00:00Current
6.2Medium risk
Vulners AI Score6.2
CVSS 39.8
CVSS 210
2