LangChain4j: SQL injection via metadata filters in langchain4j-mariadb and langchain4j-pgvector
CVE-2026-55405GHSA-2mfg-cc43-9pcj
What to do
Vendor fix available. Upgrade each affected package to the fixed version on its release line (dev.langchain4j:langchain4j-mariadb 1.16.3-beta26, 1.11.8-beta19, 1.5.1-beta11, 1.2.1-beta8; dev.langchain4j:langchain4j-pgvector 1.16.3-beta26, 1.11.8-beta19, 1.5.1-beta11, 1.2.1-beta8), redeploy, then verify what is actually installed.
This page has no inventory attached, so it cannot say whether you are affected. A vendor fix is not proof that your deployment is fixed.
Affected packages
Maven dev.langchain4j:langchain4j-mariadb
- Affected
- <= 1.2.0-beta8>= 1.3.0-beta9, <= 1.5.0-beta11>= 1.6.0-beta12, <= 1.11.7-beta19>= 1.12.1-beta21, <= 1.16.2-beta26
- Fixed in
- 1.2.1-beta8, 1.16.3-beta26, 1.5.1-beta11, 1.11.8-beta19
Maven dev.langchain4j:langchain4j-pgvector
- Affected
- <= 1.2.0-beta8>= 1.3.0-beta9, <= 1.5.0-beta11>= 1.6.0-beta12, <= 1.11.7-beta19>= 1.12.1-beta21, <= 1.16.2-beta26
- Fixed in
- 1.2.1-beta8, 1.16.3-beta26, 1.5.1-beta11, 1.11.8-beta19
Sources
- GitHub Advisory Database and maintainer security advisories on GitHub
GitHub-reviewed advisory GHSA-2mfg-cc43-9pcj lists affected ranges: Maven dev.langchain4j:langchain4j-mariadb >=0 =1.3.0-beta9 =1.6.0-beta12 =1.12.1-beta21 =0 =1.3.0-beta9 =1.6.0-beta12 =1.12.1-beta21 <=1.16.2-beta26
VerifiedObserved Structured GitHub Advisory Database record (type=reviewed) from the GitHub REST API.
Severity and exploitation
- Exploitation
- No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.
- CVSS
- 7.6 · CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L
- EPSS
- CVE-2026-55405: 0.47% estimated exploitation activity in the next 30 days; percentile 41.06 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.
Source description
As published by the source; long descriptions are shortened.
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, COMBINEDJSON / COMBINEDJSONB). 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 pgsleep(1) IS NOT NULL --") injects a live pgsleep(1) (observable as a delay; exploitable for blind data extraction). pgvector — column mode (COLUMNPERKEY). ColumnFilterMapper used the key as a bare, unquoted, unvalidated SQL identifier (<key::<type), so a key such as 1=1 OR true -- injects directly.…
Dates and revisions
- Published by the source
- Last modified by the source
- Source last checked
- Revision 1 · created ·
Published from ghsa record GHSA-2mfg-cc43-9pcj
Agent brief
Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.
# Patch Next advisory brief: CVE-2026-55405 Advisory: LangChain4j: SQL injection via metadata filters in langchain4j-mariadb and langchain4j-pgvector IDs: CVE-2026-55405, GHSA-2mfg-cc43-9pcj Record: https://patchnext.com/advisories/cve-2026-55405 (revision 1, source checked 26 Oct 2026, 16:54 UTC) Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected. Severity: High (CVSS 7.6) Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV. Vendor response: Vendor fix available; fixed versions by package: dev.langchain4j:langchain4j-mariadb 1.16.3-beta26, 1.11.8-beta19, 1.5.1-beta11, 1.2.1-beta8; dev.langchain4j:langchain4j-pgvector 1.16.3-beta26, 1.11.8-beta19, 1.5.1-beta11, 1.2.1-beta8. A vendor fix does not mean a deployment is fixed. ## Affected components - Maven dev.langchain4j:langchain4j-mariadb: affected <= 1.2.0-beta8; >= 1.3.0-beta9, <= 1.5.0-beta11; >= 1.6.0-beta12, <= 1.11.7-beta19; >= 1.12.1-beta21, <= 1.16.2-beta26; fixed in 1.2.1-beta8, 1.16.3-beta26, 1.5.1-beta11, 1.11.8-beta19 - Maven dev.langchain4j:langchain4j-pgvector: affected <= 1.2.0-beta8; >= 1.3.0-beta9, <= 1.5.0-beta11; >= 1.6.0-beta12, <= 1.11.7-beta19; >= 1.12.1-beta21, <= 1.16.2-beta26; fixed in 1.2.1-beta8, 1.16.3-beta26, 1.5.1-beta11, 1.11.8-beta19 ## Suggested inspection (read-only) - Maven dev.langchain4j:langchain4j-mariadb: check the installed version with your package manager. - Maven dev.langchain4j:langchain4j-pgvector: check the installed version with your package manager. ## Supported action Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version. ## Required regression checks - Run the test suite and a production build. - Exercise the features that depend on dev.langchain4j:langchain4j-mariadb, dev.langchain4j:langchain4j-pgvector. - Repeat the inspection and confirm that only fixed versions remain installed. ## Rollback considerations - Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward. ## Unresolved questions - Which deployments run an affected version? - Exploitation status can change. Check again before lowering the priority. - Mark the work resolved only after the fixed version is verified in production. ## Sources - Verified: https://github.com/advisories/GHSA-2mfg-cc43-9pcj (GitHub-reviewed advisory GHSA-2mfg-cc43-9pcj lists affected ranges: Maven dev.langchain4j:langchain4j-mariadb >=0 =1.3.0-beta9 =1.6.0-beta12 =1.12.1-beta21 =0 =1.3.0-beta9 =1.6.0-beta12 =1.12.1-beta21 <=1.16.2-beta26) Commands are suggestions: review each one before running it.
Loading voting…