VRT Sign in

Dev.langchain4j CVEs

1 CVE, 1 protected by Waratek

Look up CVE IDs Status Exploitation Severity

Reset

Overview 1 match · 0 exploited · 0 CISA KEV · 0 public PoC · 0 EPSS ≥ 0.5

1match 0exploited0.0% 0CISA KEV0.0% 0public PoC0.0% 0EPSS ≥ 0.50.0%

Protected by Waratek 1 100.0% Rule in development 0 0.0% Mitigation candidate 0 0.0% No exploit published 0 0.0%

Critical 0 0.0% High 1 100.0% Medium 0 0.0% Low 0 0.0% None 0 0.0% Unknown 0 0.0%

blocked by ARMR today 1 100.0% partly blocked 0 0.0% not blocked 0 0.0% not established 0 0.0% unrecorded 0 0.0%

Exploited 0 0.0% Working exploit published 0 0.0% Proof of concept only 0 0.0% Forecast only 0 0.0% No public exploit 1 100.0%

split by StatusSeverityProtectionExploit maturity peak 1 / month

Jul 261 Protected by Waratek1 High1 blocked by ARMR today1 No public exploit1

Jul 26

1 match Sign in to download these CVEs as CSV or JSON, or to follow them in a feed.

CVE	Severity	Published▾	Status	Exploitation	Description
CVE-2026-55405	High	2026-07-10	Protected by Waratek	No public exploit	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.

CVE

Severity

Published▾

Status

Exploitation

Description

CVE-2026-55405

High

2026-07-10

Protected by Waratek

No public exploit

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.