High

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

  • Disclosed: 17.06.2026
  • Updated: 11.10.2026 12:22

Summary

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.

Details

pgvector — JSON mode (default, COMBINED_JSON / COMBINED_JSONB). JSONFilterMapper places the key inside a single-quoted SQL literal (the JSON key of the ->> operator) with no escaping:

(metadata->>'<key>')::text

A key containing a single quote breaks out, e.g. metadataKey("')::text IS NOT NULL OR pg_sleep(1) IS NOT NULL --") injects a live pg_sleep(1) (observable as a delay; exploitable for blind data extraction).

pgvector — column mode (COLUMN_PER_KEY). ColumnFilterMapper used the key as a bare, unquoted, unvalidated SQL identifier (<key>::<type>), so a key such as 1=1 OR true -- injects directly.

MariaDB — JSON mode (default). JSONFilterMapper placed the key inside the JSON path literal '$.<key>' unescaped (same break-out mechanism). Additionally, MariaDbFilterMapper.formatValue() escaped ' but not \; because MariaDB treats backslash as an escape character by default, a string value ending in a backslash could also break out of its literal.

MariaDB — column mode (COLUMN_PER_KEY). ColumnFilterMapper fell back to the raw, unescaped key when the driver could not quote it as an identifier (e.g. a character).

The filter key is the runtime injection surface; both stores' search() (including pgvector's HYBRID mode) and removeAll(Filter) are affected. Add/upsert operations a parameterized and not affected.

Impact

Applications that allow attacker-influenced metadata filter keys (e.g. use LLM-generated filters) to reach these stores are exposed to SQL injection: blind data exfiltration, denial of service via sleep functions, and — through `remove deletion of arbitrary rows. Applications using only hard-coded, developer-defined filter keys are not reachable.

Patches

Fixed in langchain4j-mariadb and langchain4j-pgvector 1.16.3-beta26:

  • JSON filter keys are escaped before being embedded in the SQL string lit quotes doubled, correct for PostgreSQL standard_conforming_strings = on; MariaDB: backslash and single quote).
  • MariaDB string values escape both \ and '.
  • Column-mode keys are validated/quoted as identifiers and rejected when u concatenated as raw SQL.

Workarounds

  • Do not pass untrusted input as metadata filter keys.
  • Restrict filter keys to a known allow-list at the application layer.

References

  • pgvector: JSONFilterMapper, ColumnFilterMapper
  • MariaDB: JSONFilterMapper, MariaDbFilterMapper, ColumnFilterMapper

Affected software

Click a technology to see all vulnerabilities affecting it.

PlatformPackageVulnerable versionsFixed in
Java / Kotlin (Maven) dev.langchain4j:langchain4j-mariadb < 1.2.1-beta8, >= 1.3.0-beta9, < 1.5.1-beta11, >= 1.6.0-beta12, < 1.11.8-beta19, >= 1.12.1-beta21, < 1.16.3-beta26 1.2.1-beta8, 1.5.1-beta11, 1.11.8-beta19, 1.16.3-beta26
Java / Kotlin (Maven) dev.langchain4j:langchain4j-pgvector < 1.2.1-beta8, >= 1.3.0-beta9, < 1.5.1-beta11, >= 1.6.0-beta12, < 1.11.8-beta19, >= 1.12.1-beta21, < 1.16.3-beta26 1.2.1-beta8, 1.5.1-beta11, 1.11.8-beta19, 1.16.3-beta26

References

CVSS score 7.6/10
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L
Weakness (CWE)
CWE-89
Platform
Java / Kotlin (Maven)
Package
dev.langchain4j:langchain4j-mariadb, dev.langchain4j:langchain4j-pgvector
Disclosed
17.06.2026
Updated
11.10.2026 12:22

Sources and licenses

OSV / GitHub Advisory Database - GHSA-2mfg-cc43-9pcj - CC BY 4.0

Vulnerability history: dev.langchain4j:langchain4j-mariadb

All published vulnerabilities of this package (Java / Kotlin (Maven)), newest first. Shows whether this is a one-off slip or a package that needs watching.

This is the only known vulnerability of this package.

Know which vulnerabilities affect your application

With the DockRay integration and software inventory enabled, DockRay checks reported component versions against known vulnerabilities and notifies you about confirmed matches. Coverage depends on the supported technology and available advisory data.

Connect your application
DockRay newsletter

Application security in your inbox

Important vulnerabilities, actionable guidance and practical advice for your applications. Choose your technologies and follow what matters to your project.

  • A daily digest of new vulnerabilities, critical ones included.
  • Notifications about important updates.
  • Practical advice on application security and monitoring.

Leave empty to receive updates for every technology.

Free to subscribe. Unsubscribe with one click in any email.