CVE-2026-44843: CWE-502: Deserialization of Untrusted Data in langchain-ai langchain
LangChain versions prior to 0.3.85 and between 1.0.0a1 and before 1.3.3 contain a deserialization vulnerability. The framework uses overly broad allowlists when deserializing certain runtime inputs, allowing trusted LangChain-serializable objects to be instantiated with untrusted constructor arguments. This can lead to unintended object instantiation during deserialization. The vulnerability is identified as CWE-502 and has a high severity with a CVSS score of 8.
AI Analysis
Technical Summary
LangChain is affected by a deserialization of untrusted data vulnerability (CWE-502) in versions prior to 0.3.85 and from 1.0.0a1 up to but not including 1.3.3. The issue arises because certain runtime code paths deserialize inputs using an overly broad allowlist, specifically calling load() with allowed_objects="all". While this does not permit arbitrary Python object deserialization, it allows any trusted LangChain-serializable object to be revived, which is broader than necessary. Consequently, attacker-supplied serialized constructor dictionaries may cause trusted runtime paths to instantiate classes with untrusted constructor arguments. This vulnerability is addressed by updates in versions 0.3.85 and 1.3.3.
Potential Impact
Successful exploitation could allow an attacker to supply crafted serialized data that causes the application to instantiate objects with untrusted constructor arguments. This may lead to unauthorized information disclosure (high confidentiality impact) and limited integrity impact. There is no reported impact on availability. No known exploits are currently reported in the wild.
Mitigation Recommendations
Upgrading LangChain to version 0.3.85 or later, or 1.3.3 or later, fully addresses this vulnerability. No other official remediation or temporary fixes are documented. Users should apply these updates to ensure the vulnerability is mitigated.
CVE-2026-44843: CWE-502: Deserialization of Untrusted Data in langchain-ai langchain
Description
LangChain versions prior to 0.3.85 and between 1.0.0a1 and before 1.3.3 contain a deserialization vulnerability. The framework uses overly broad allowlists when deserializing certain runtime inputs, allowing trusted LangChain-serializable objects to be instantiated with untrusted constructor arguments. This can lead to unintended object instantiation during deserialization. The vulnerability is identified as CWE-502 and has a high severity with a CVSS score of 8.
CVSS v3.1
Score 8.2high
Affected software
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
LangChain is affected by a deserialization of untrusted data vulnerability (CWE-502) in versions prior to 0.3.85 and from 1.0.0a1 up to but not including 1.3.3. The issue arises because certain runtime code paths deserialize inputs using an overly broad allowlist, specifically calling load() with allowed_objects="all". While this does not permit arbitrary Python object deserialization, it allows any trusted LangChain-serializable object to be revived, which is broader than necessary. Consequently, attacker-supplied serialized constructor dictionaries may cause trusted runtime paths to instantiate classes with untrusted constructor arguments. This vulnerability is addressed by updates in versions 0.3.85 and 1.3.3.
Potential Impact
Successful exploitation could allow an attacker to supply crafted serialized data that causes the application to instantiate objects with untrusted constructor arguments. This may lead to unauthorized information disclosure (high confidentiality impact) and limited integrity impact. There is no reported impact on availability. No known exploits are currently reported in the wild.
Mitigation Recommendations
Upgrading LangChain to version 0.3.85 or later, or 1.3.3 or later, fully addresses this vulnerability. No other official remediation or temporary fixes are documented. Users should apply these updates to ensure the vulnerability is mitigated.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-05-07T21:21:48.352Z
- Cvss Version
- 3.1
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a16041de29bf47b505ea069
Added to database: 05/26/2026, 20:35:41 UTC
Last enriched: 06/02/2026, 21:17:25 UTC
Last updated: 07/31/2026, 19:22:59 UTC
Views: 56
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
External Links
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.