CVE-2026-97869: langchain4j · Deserialization
Affects langchain4jSource CVE Database V5
Public exploit available · CVSS 2.1 Low.
Data as of 9 Nov 2026, 23:24 UTC
- EPSS
- 0.2% chance of exploitation in 30 days – higher than 15% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
CVSS:4.0/AV:N/AC:H/AT:N/PR:H/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:PExploitation evidence
Disclosed: evidence found.
CVE published 25 Sep 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: evidence found.
CVSS exploit maturity: proof of concept public
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), CVSS vector, the Metasploit, Exploit-DB and nuclei-templates index as of 9 Nov 2026.
What to do
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| langchain4j | Affected
| Fixed in– |
Mavenio.github.langchain4j/langchain4j-agenticpkg:maven/io.github.langchain4j/langchain4j-agenticOther threats | Affected
| Fixed in– |
CPE configurations (1)
cpe:2.3:a:langchain4j:langchain4j:*:*:*:*:*:*:*:*
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
Upgrade langchain4j to versions 1.5.3-beta11, 1.11.10-beta19, or 1.18.1-beta28 or later, where this vulnerability has been fixed. Additionally, ensure that AgenticScope persistence is disabled unless explicitly required, as exploitation requires this feature to be enabled. No further action is necessary if the application does not enable AgenticScope persistence or does not allow untrusted write access to the persistence store.
Description
CVE-2026-97869 is a deserialization vulnerability in the langchain4j library affecting specific beta versions. It impacts the AgenticScopeSerializer.fromJson function in the LangChain4j-agentic component. Exploitation requires that AgenticScope persistence is enabled (which is opt-in) and that an attacker already has write access to the persistent store. The vulnerability has a low severity score and a high attack complexity, making exploitation difficult. Fixed versions have been released shortly after the issue was reported privately.
References
- vuldb.com/vuln/409886 (opens in a new tab)
- vuldb.com/vuln/409886/cti (opens in a new tab)
- vuldb.com/cve/CVE-2026-97869 (opens in a new tab)
- vuldb.com/submit/911825 (opens in a new tab)
- github.com/langchain4j/langchain4j/security/advisories/GHSA-gmwr-7wmf-mrjm (opens in a new tab)
- github.com/afish3201-debug/CVE/blob/main/Insecure%20Jackson%20Default%20Typing%20Leads%20to%20Arbitrary%20Class%20Instantiation%20in%20LangChain4j%20Agentic%20Module.md (opens in a new tab)
- github.com/langchain4j/langchain4j/releases/tag/1.18.1 (opens in a new tab)
- github.com/langchain4j/langchain4j/ (opens in a new tab)