CVE-2026-97869

Overview

LangChain4j up to 1.5.3-beta10, 1.11.10-beta18, and 1.18.1-beta27 contains a deserialization flaw in AgenticScopeSerializer.fromJson that can be triggered by crafted JSON when AgenticScope persistence is enabled, allowing remote code execution. The vulnerability is already published and exploitable by attackers who can write to the persistence store. Upgrading to the patched releases resolves the issue.

Description

A flaw has been found in langchain4j up to 1.5.3-beta10/1.11.10-beta18/1.18.1-beta27. This vulnerability affects the function AgenticScopeSerializer.fromJson of the file AgenticScopeJsonSerializationIT.java of the component LangChain4j-agentic. This manipulation causes deserialization. Remote exploitation of the attack is possible. The attack's complexity is rated as high. It is stated that the exploitability is difficult. The exploit has been published and may be used. Upgrading to version 1.5.3-beta11, 1.11.10-beta19 and 1.18.1-beta28 is able to resolve this issue. Upgrading the affected component is advised. The project maintainer kindly explains: "The issue was reported to us privately on 23 July 2026 and fixed in releases published on 29 July 2026. It is tracked as GHSA-gmwr-7wmf-mrjm. Exploitation requires an application to have enabled AgenticScope persistence, which is opt-in, and an attacker who can already write to that store. All maintained release lines have been patched.

Impact

The flaw compromises confidentiality, integrity, and availability of any system that processes untrusted AgenticScope JSON. Attackers who can write to the persistence store can execute arbitrary code, potentially taking full control of the host. Defenders should treat this as a high‑risk flaw for exposed services.

Remediation

Upgrade LangChain4j to 1.5.3-beta11, 1.11.10-beta19, or 1.18.1-beta28 (or later). If an upgrade is not immediately possible, disable AgenticScope persistence or restrict write access to the persistence store. Monitor logs for suspicious JSON deserialization activity and apply any available security patches promptly.

Risk context

Severity is medium (CVSS 4.1) but the exploit is already published and requires remote code execution. The high complexity and difficulty mean the risk is moderate; defenders should act promptly but the threat is not imminent. No EPSS data is available.

Affected products

• LangChain4j 1.5.3-beta10
• LangChain4j 1.11.10-beta18
• LangChain4j 1.18.1-beta27
• LangChain4j-agentic component