LangChain4j Metadata Filter EmbeddingSearchRequest.filter injection

Summaryinfo

A vulnerability classified as critical has been found in LangChain4j up to 1.2.1-beta7/1.5.1-beta10/1.11.8-beta18/1.16.3-beta25. This affects the function EmbeddingSearchRequest.filter of the component Metadata Filter Handler. The manipulation leads to injection. This vulnerability is documented as CVE-2026-55405. The attack can be initiated remotely. There is not any exploit available.

Detailsinfo

A vulnerability was found in LangChain4j up to 1.2.1-beta7/1.5.1-beta10/1.11.8-beta18/1.16.3-beta25. It has been rated as critical. This issue affects the function EmbeddingSearchRequest.filter of the component Metadata Filter Handler. The manipulation with an unknown input leads to a injection vulnerability. Using CWE to declare the problem leads to CWE-74. The product constructs all or part of a command, data structure, or record using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify how it is parsed or interpreted when it is sent to a downstream component. Impacted is confidentiality, integrity, and availability. The summary by CVE is:

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.

The advisory is shared at github.com. The identification of this vulnerability is CVE-2026-55405 since 06/16/2026. The exploitation is known to be easy. The attack may be initiated remotely. No form of authentication is needed for a successful exploitation. Technical details are known, but no exploit is available. MITRE ATT&CK project uses the attack technique T1055 for this issue.

Upgrading to version 1.2.1-beta8, 1.5.1-beta11, 1.11.8-beta19 or 1.16.3-beta26 eliminates this vulnerability.

If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Productinfo

Name

• LangChain4j

Version

• 1.2.1-beta1
• 1.2.1-beta2
• 1.2.1-beta3
• 1.2.1-beta4
• 1.2.1-beta5
• 1.2.1-beta6
• 1.2.1-beta7
• 1.5.1-beta10
• 1.11.8-beta18
• 1.16.3-beta25

Website

• Product: https://github.com/langchain4j/langchain4j/

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Discussion