Lucene search
+L

8 matches found

RedhatCVE
RedhatCVE
•added 2026/06/05 7:50 p.m.•25 views

CVE-2026-44843

A flaw was found in LangChain, a framework for building agents and large language model LLM-powered applications. Older runtime code paths within LangChain deserialize application-controlled payloads using overly broad object allowlists. A remote attacker can exploit this by supplying specially...

8.2CVSS7.1AI score0.00406EPSS
SaveExploits0References4
NVD
NVD
•added 2026/05/26 9:16 p.m.•35 views

CVE-2026-44843

LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load with...

8.2CVSS0.00406EPSS
SaveExploits0References1
osv_cve
osv_cve
•added 2026/05/26 7:47 p.m.•28 views

CVE-2026-44843 LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlists

LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load with...

8.2CVSS7.4AI score0.00406EPSS
SaveExploits0References3
EUVD
EUVD
•added 2026/05/26 7:47 p.m.•47 views

EUVD-2026-31976

LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load with...

8.2CVSS7.4AI score0.00406EPSS
SaveExploits0References1
attackerkb
attackerkb
•added 2026/05/26 7:47 p.m.•30 views

CVE-2026-44843

LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load with...

8.2CVSS7.4AI score0.00406EPSS
SaveExploits0References2Affected Software1
Vulnrichment
Vulnrichment
•added 2026/05/26 7:47 p.m.•36 views

CVE-2026-44843 LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlists

LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load with...

8.2CVSS7.4AI score0.00406EPSS
SaveExploits0References1
osv_ghsa
osv_ghsa
•added 2026/05/08 11:07 p.m.•21 views

GHSA-PJWX-R37V-7724 LangChain vulnerable to unsafe deserialization of attacker-controlled objects through overly broad `load()` allowlists

LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load with allowedobjects="all". This does not enable arbitrary Python object deserialization, but it does allow...

8.2CVSS7.1AI score0.00406EPSS
SaveExploits0References3
Microsoft KB
Microsoft KB
•added 2022/05/24 12:00 a.m.•30 views

May 24, 2022—KB5014021 (OS Build 20348.740) Preview

May 24, 2022—KB5014021 OS Build 20348.740 Preview Applies To Windows Server 2022 Note For information about Windows update terminology, see the article about the types of Windows updates and the monthly quality update types. For an overview of Windows Server 2022, see its update history page. Not...

5.7AI score
SaveExploits0
Rows per page
Query Builder