GHSA-C67J-W6G6-Q2CM LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs

Summary A serialization injection vulnerability exists in LangChain's dumps and dumpd functions. The functions do not escape dictionaries with 'lc' keys when serializing free-form dictionaries. The 'lc' key is used internally by LangChain to mark serialized objects. When user-controlled data...

accessiqlue (2025.12.21154255), agentmanager (>=0.1.0, <=0.1.1) +310 more potentially affected by CVE-2025-68664 via langchain-core (>=1.0.0, <=1.2.4)

langchain-core PYPI version =1.0.0, =0.1.0, =3.0.3, =4.0.6 and more Source cves: CVE-2025-68664 Source advisory: OSV:GHSA-C67J-W6G6-Q2CM...

EUVD-2025-204849

LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs...

CVE-2025-68665: Deserialization of Untrusted Data

LangChain is a framework for building LLM-powered applications. Prior to @langchain/core versions 0.3.80 and 1.1.8, and prior to langchain versions 0.3.37 and 1.2.3, a serialization injection vulnerability exists in LangChain JS's toJSON method and subsequently when string-ifying objects using...

LangChain code-related vulnerabilities

LangChain is a LangChain open source framework for developing applications powered by the Large Language Model LLM. A code issue vulnerability exists in LangChain versions prior to 0.3.37 and prior to 1.2.3, which stems from serialization injection and could lead to the execution of arbitrary cod...

CVE-2025-68664: Deserialization of Untrusted Data

LangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, a serialization injection vulnerability exists in LangChain's dumps and dumpd functions. The functions do not escape dictionaries with 'lc' keys when serializing free-form dictionaries...

LangChain code-related vulnerabilities

LangChain is a LangChain open source framework for developing applications powered by the Large Language Model LLM. A code issue vulnerability exists in LangChain versions prior to 0.3.81 and prior to 1.2.5, which stems from serialization injection and could lead to the execution of arbitrary cod...

PT-2025-52859

Name of the Vulnerable Software and Affected Versions: LangChain versions prior to 0.3.81 and 1.2.5 Description: A serialization injection vulnerability exists in LangChain's dumps and dumpd functions. These functions do not properly escape dictionaries containing 'lc' keys when serializing data...

PT-2025-52862

Name of the Vulnerable Software and Affected Versions LangChain versions prior to 0.3.37 @langchain/core versions prior to 0.3.80 LangChain versions prior to 1.2.3 @langchain/core versions prior to 1.1.8 Description LangChain is a framework designed for building applications powered by Large...

cognee (>=0.1.37, <=0.2.1.dev0), langchain-cognee (0.1.0) potentially affected by CVE-2025-68481 via fastapi-users (14.0.1)

fastapi-users PYPI version 14.0.1 is affected by a known vulnerability. The following packages have a transitive dependency on fastapi-users and may be impacted: - cognee =0.1.37, =0.2.1.dev0 - langchain-cognee 0.1.0 Source cves: CVE-2025-68481 Source advisory: OSV:GHSA-5J53-63W8-8625...

Path Traversal

Langchain-Chatchat is vulnerable to Path Traversal. The vulnerability is due to improper validation of the flag argument when processing requests to the /v1/file endpoint, which allows an attacker to manipulate file paths and access files outside the intended directory...

Template Injection

langchain-core is vulnerable to Template Injection. The vulnerability is due to the lack of validation in template strings, where attackers can access Python object internals through template syntax. This allows attackers to extract sensitive information from object internals and potentially...

langgraph SQL injection vulnerability

langgraph is a large modeling framework open source by LangChain. An SQL injection vulnerability exists in langgraph 3.0.0 and earlier versions, which stems from an unvalidated metadata filter key that could lead to an SQL injection attack...

CVE-2025-65106

A template-injection vulnerability in LangChain's prompt template system allowed untrusted template strings to access Python object internals through attribute traversal and indexing. By crafting malicious template expressions, an attacker could read sensitive properties e.g., class, globals from...

CVE-2025-65106

LangChain is a framework for building agents and LLM-powered applications. From versions 0.3.79 and prior and 1.0.0 to 1.0.6, a template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This...

a-data-processing (0.0.1), a2a-client-handler (0.1.0) +1121 more potentially affected by CVE-2025-65106 via langchain-core (>=0.0.1, <=0.3.79)

langchain-core PYPI version =0.0.1, =0.1.0, =0.1.3, =0.1.0b0, =4.8.2, =0.1.3, =0.1.0, =3.2.0, =2.1.7, =0.0.2, =0.0.5 - agentc-langchain 1.0.0 and more Source cves: CVE-2025-65106 Source advisory: SNYK:PYTHON-LANGCHAINCORE-14100977...

accessiqlue (2025.12.21154255), agent-builder (>=0.0.2, <=0.1.7) +320 more potentially affected by CVE-2025-65106 via langchain-core (>=0.4.0.dev0, <=1.0.5)

langchain-core PYPI version =0.4.0.dev0, =0.0.2, =0.1.0, =0.1.1 - ai-benchmark-analyzer 2025.12.21193050 - ai-claim-essence 2025.12.20202921 - ai-design-insights 2025.12.21145447 - ai-mysql-translator 2025.12.21101721 - ai-reliability-analyzer 2025.12.21171415 - ai-risk-extractor 2025.12.21102659...

Template Injection

Overview langchain-core is a Building applications with LLMs through composability Affected versions of this package are vulnerable to Template Injection in the prompt template system. An attacker can access internal Python object attributes by submitting specially crafted template strings to...

CVE-2025-65106 LangChain Vulnerable to Template Injection via Attribute Access in Prompt Templates

LangChain is a framework for building agents and LLM-powered applications. From versions 0.3.79 and prior and 1.0.0 to 1.0.6, a template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This...

CVE-2025-65106 LangChain Vulnerable to Template Injection via Attribute Access in Prompt Templates

LangChain is a framework for building agents and LLM-powered applications. From versions 0.3.79 and prior and 1.0.0 to 1.0.6, a template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This...