CVE-2026-55405 LangChain4j: SQL injection via metadata filters in langchain4j-mariadb and langchain4j-pgvector

What is CVE-2026-55405?

CVE-2026-55405 is a high-severity SQL injection vulnerability in langchain4j, published on 10 Jul 2026. Any signed-in user can exploit it over the network, with no action from the victim.

Official 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.

Weakness: CWE-89

Which versions are affected by CVE-2026-55405?

16 open source packages ship an affected version, including dev.langchain4j:langchain4j-mariadb and dev.langchain4j:langchain4j-pgvector.

How do I fix CVE-2026-55405?

Upgrade dev.langchain4j:langchain4j-mariadb to a fixed version for your release line: 1.2.1-beta8, 1.16.3-beta26, 1.5.1-beta11 or 1.11.8-beta19.

Use parameterised queries everywhere and never build SQL by joining strings. Upgrade affected software first; a web application firewall only buys time. More about SQL injection.

Is CVE-2026-55405 being exploited?

There is no known exploitation of CVE-2026-55405 in the wild and no public exploit code.

Sources

• CVE record
• NVD
• OSV
• GitHub advisory
• How this page is made

Also known as GHSA-2mfg-cc43-9pcj.