7.6
HIGH CVSS 3.1
CVE-2026-55405
LangChain4j: SQL injection via metadata filters in langchain4j-mariadb and langchain4j-pgvector
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.

INFO

Published Date :

July 10, 2026, 9:16 p.m.

Last Modified :

July 10, 2026, 9:16 p.m.

Remotely Exploit :

Yes !
Affected Products

The following products are affected by CVE-2026-55405 vulnerability. Even if cvefeed.io is aware of the exact versions of the products that are affected, the information is not represented in the table below.

No affected product recoded yet

CVSS Scores
The Common Vulnerability Scoring System is a standardized framework for assessing the severity of vulnerabilities in software and systems. We collect and displays CVSS scores from various sources for each CVE.
Score Version Severity Vector Exploitability Score Impact Score Source
CVSS 3.1 HIGH [email protected]
Solution
Update LangChain4j MariaDB and pgvector embedding stores to fixed versions to prevent SQL injection.
  • Update langchain4j-mariadb and langchain4j-pgvector to fixed versions.
  • Ensure filter keys are properly escaped in SQL queries.
  • Review metadata filtering logic for security.
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-55405 is associated with the following CWEs:

We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2026-55405 vulnerability anywhere in the article.

The following table lists the changes that have been made to the CVE-2026-55405 vulnerability over time.

Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.

  • New CVE Received by [email protected]

    Jul. 10, 2026

    Action Type Old Value New Value
    Added Affected [{'vendor': 'langchain4j', 'product': 'langchain4j', 'versions': [{'status': 'affected', 'version': '< 1.2.1-beta8'}, {'status': 'affected', 'version': '>= 1.3.0-beta9, < 1.5.1-beta11'}, {'status': 'affected', 'version': '>= 1.6.0-beta12, < 1.11.8-beta19'}, {'status': 'affected', 'version': '>= 1.12.1-beta21, < 1.16.3-beta26'}]}]
    Added 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.
    Added CVSS V3.1 AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L
    Added CWE CWE-89
    Added Reference https://github.com/langchain4j/langchain4j/commit/13a0698bdfaf105d8aaf0367881df51358596219
    Added Reference https://github.com/langchain4j/langchain4j/commit/1bc1f60aa58ef5c3c1703caf73362482480351cf
    Added Reference https://github.com/langchain4j/langchain4j/commit/8805d5d128694302f1b0a2650174186862f669e7
    Added Reference https://github.com/langchain4j/langchain4j/commit/ce96291dfb243c7f6753b5d65c7a77914642314f
    Added Reference https://github.com/langchain4j/langchain4j/commit/f14a10ce77e4ea1b8277f67d6a81f46abd7a5bc2
    Added Reference https://github.com/langchain4j/langchain4j/releases/tag/1.16.3
    Added Reference https://github.com/langchain4j/langchain4j/security/advisories/GHSA-2mfg-cc43-9pcj
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.