SEPTEMBER 19, 2026
Live Feed
Back to database
Case File

CVE-2026-55405

HIGH · CVSS 7.6 EPSS 0.35% Public Exploit

Source: NVD + CISA KEV + EPSS · Published 2026-07-10 · Last synced 2026-08-09

CyberRota Analysis

AI-Generated

The vulnerability affects the LangChain4j Java library, specifically in the MariaDB and pgvector embedding stores, where inadequate escaping of filter keys allows for SQL injection through crafted metadata keys in the EmbeddingSearchRequest.filter() method. This can lead to severe impacts such as unauthorized data exfiltration, denial of service, and arbitrary data deletion. Organizations utilizing affected versions of LangChain4j should prioritize updating to the patched versions to mitigate these risks.

Public Exploit Signal

A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.

Note: these links are listed for security research and verification purposes only.

CVE
CVE-2026-55405
Severity
HIGH
CVSS
7.6
EPSS
0.35%
Java

Original NVD Description

LangChain4j is a Java library for building LLM-powered applications on the JVM. Prior to 1.2.1-beta8, 1.5.1-beta11, 1.11.8-beta19, and 1.16.3-beta26, the MariaDB and pgvector embedding stores build metadata-filter SQL by string-concatenating filter keys, and in MariaDB string values, directly into the query without adequate escaping. A crafted metadata key in EmbeddingSearchRequest.filter() can break out of its SQL context and inject arbitrary SQL into the statements executed by the stores' search and removeAll(Filter) operations, enabling blind data exfiltration, denial of service via sleep functions, and deletion of arbitrary rows through removeAll(Filter). This issue is fixed in langchain4j-mariadb and langchain4j-pgvector versions 1.2.1-beta8, 1.5.1-beta11, 1.11.8-beta19, and 1.16.3-beta26.