- CVSS
- HIGH · 7.6v3.1CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L
- Published
- 2026-07-10
- Weakness
- CWE-89
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-55405
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.
References
- https://github.com/langchain4j/langchain4j/commit/13a0698bdfaf105d8aaf0367881df51358596219
- https://github.com/langchain4j/langchain4j/commit/1bc1f60aa58ef5c3c1703caf73362482480351cf
- https://github.com/langchain4j/langchain4j/commit/8805d5d128694302f1b0a2650174186862f669e7
- https://github.com/langchain4j/langchain4j/commit/ce96291dfb243c7f6753b5d65c7a77914642314f
- https://github.com/langchain4j/langchain4j/commit/f14a10ce77e4ea1b8277f67d6a81f46abd7a5bc2
- https://github.com/langchain4j/langchain4j/releases/tag/1.16.3
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-55405 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.