CVE-2026-34070

我在 LangChain 中发现了一个路径遍历漏洞，可能泄露你的云凭证 AI 最流行框架之一中被遗忘的遗留 API，如何悄然让数百万应用暴露于任意文件读取风险之下。 当你写的概念验证代码第一次运行就成功时，会有一种特别的感觉。不完全是兴奋——更像是一种缓慢而不安的醒悟：刚刚真的发生了什么。当我用测试配置运行 loadpromptfromconfig，看着一个本不该被读取的文件内容直接打印到终端时，就是这种感觉。 这就是 CVE-2026-34070 的故事：一个存在于 langchain-core 中的路径遍历漏洞，现已在 1.2.22 版本中修复。 为什么是 LangChain？...

CVE-2025-68664

CVE-2025-68664 这一切我想在圣诞节得到的就是你们的秘密：LangGrinch 袭击了 LangChain 核心 CVE-2025-68664 作者：亚尔登·波拉特 Cyata 研究：LangChain 中的 LangGrinch 漏洞 已发布：https://cyata.ai/blog/langgrinch-langchain-core-cve-2025-68664/ 昨天，LangChain 发布了一个关于我在 langchain-core 中发现的漏洞的关键警告：CVE-2025-68664 / GHSA-c67j-w6g6-q2cm。...

LangChain-Core < 0.3.81 / 1.x < 1.2.5

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...

langgrinch-cve-2025-68664-analysis

LangGrinch漏洞分析：CVE-2025-68664 概述 本仓库包含一份关于CVE-2025-68664（又名LangGrinch）的技术报告，该漏洞是影响LangChain Core的反序列化注入漏洞。 报告阐述了漏洞背景、根本原因、利用流程、威胁模型、缓解策略以及对基于LLM的应用的实际安全影响。 涵盖主题 LangChain序列化与反序列化 不安全的反序列化 / CWE-502 LLM应用安全 作为传递路径的提示注入 秘密暴露风险 STRIDE威胁建模 缓解措施与安全编码实践 报告 完整报告请见： LangGrinch CVE-2025-68664报告 关键要点...

ROOT-APP-PYPI-CVE-2026-44843 CVE-2026-44843 in langchain-core - Patched by Root

Root has patched CVE-2026-44843 in the langchain-core package for Root:PyPI. Multiple fixed versions available...

ROOT-APP-PYPI-CVE-2026-34070 CVE-2026-34070 in langchain-core - Patched by Root

Root has patched CVE-2026-34070 in the langchain-core package for Root:PyPI. Multiple fixed versions available...

ROOT-APP-PYPI-CVE-2025-65106 CVE-2025-65106 in langchain-core - Patched by Root

Root has patched CVE-2025-65106 in the langchain-core package for Root:PyPI. Multiple fixed versions available...

ROOT-APP-PYPI-CVE-2025-68664 CVE-2025-68664 in langchain-core - Patched by Root

Root has patched CVE-2025-68664 in the langchain-core package for Root:PyPI. Multiple fixed versions available...

PYSEC-2026-1070 Malicious code in langchain-core-mcp (PyPI)

Part of the "Hades" wave of the Shai-Hulud supply-chain campaign. On 2026-06-08, malicious phantom releases of langchain-core-mcp were published to PyPI using stolen credentials. The package executes a bundled JavaScript payload via the Bun runtime on import that harvests and exfiltrates...

PYSEC-2026-1517 langchain-core allows unauthorized users to read arbitrary files from the host file system

A vulnerability in langchain-core versions =0.1.17,=0.2.0,=0.3.0,0.3.15 allows unauthorized users to read arbitrary files from the host file system. The issue arises from the ability to create langchaincore.prompts.ImagePromptTemplate's and by extension langchaincore.prompts.ChatPromptTemplate's...

Security Bulletin: Maximo AI Service uses multiple third party dependencies which are vulnerable to multiple CVEs.

Summary Maximo AI Service uses pdfminersix-20251107-py3-none-any.whl, requests-2.32.5-py3-none-any.whl, langchaincore-0.3.81-py3-none-any.whl, pythondotenv-1.0.1-py3-none-any.whl, langchaintextsplitters-0.3.11-py3-none-any.whl, qs-6.15.1.tgz, idna-3.10-py3-none-any.whl, idna-3.14-py3-none-any.whl...

Malicious code in langchain-core-mcp (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector bd42d83950d8d8fc559905eed104af38cd6c8aef683b96778f0b8d778dd6bd5a Package langchain-core-mcp impersonates the legitimate langchain-core publisher: METADATA sets Project-URL Repository to...

GHSA-PJWX-R37V-7724 vulnerabilities

Vulnerabilities for packages: py3-langchain-core, py3-langchain...

CVE-2026-44843 vulnerabilities

Vulnerabilities for packages: py3-langchain-core, py3-langchain...

CVE-2026-44843 vulnerabilities

Vulnerabilities for packages: py3-langchain, py3-langchain-core...

GHSA-PJWX-R37V-7724 vulnerabilities

Vulnerabilities for packages: py3-langchain, py3-langchain-core...

LangChain Core 1.3.2 / 0.3.84 Tracer Deserialization / Credential Disclosure

LangChain Core has a tracer deserialization vulnerability that could allow unauthenticated remote credential exfiltration in affected deployments. Versions 1.3.2 and 0.3.84 are affected...

Deserialization of Untrusted Data

Overview langchain-core is a Building applications with LLMs through composability Affected versions of this package are vulnerable to Deserialization of Untrusted Data in the load process. An attacker can instantiate trusted classes with untrusted constructor arguments by submitting specially...

📄 LangChain Core Insecure Deserialization

LangChain Core versions prior to 1.2.5 and 0.3.81 suffer from a deserialization vulnerability that allows for server-side template injection that can lead to remote code execution. Exploit Title: LangChain Core - SSTI/RCE Date: 2025-12-29 Exploit Author: Mohammed Idrees Banyamer Author Country:...

LangChain Core 1.2.4 - SSTI/RCE

Exploit Title: LangChain Core - SSTI/RCE Date: 2025-12-29 Exploit Author: Mohammed Idrees Banyamer Author Country: Jordan Contact: @banyamersecurity Instagram GitHub: https://github.com/mbanyamer Vendor Homepage: https://www.langchain.com/ Software Link: https://pypi.org/project/langchain-core/...