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 !
Source :
[email protected]
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
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | HIGH | [email protected] |
Solution
- Update langchain4j-mariadb and langchain4j-pgvector to fixed versions.
- Ensure filter keys are properly escaped in SQL queries.
- Review metadata filtering logic for security.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-55405.
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:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-55405
weaknesses.
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