CVE-2026-30617

LangChain-ChatChat 0.3.1 contains a remote code execution vulnerability in its MCP STDIO server configuration and execution handling. A remote attacker can access the publicly exposed MCP management interface and configure an MCP STDIO server with attacker-controlled commands and arguments. When...

ROOT-APP-NPM-CVE-2026-26019 CVE-2026-26019 in @rootio/langchain__community - Patched by Root

Root has patched CVE-2026-26019 in the @rootio/langchaincommunity package for Root:npm. Multiple fixed versions available...

ROOT-APP-PYPI-CVE-2026-41481 CVE-2026-41481 in rootio-langchain-text-splitters - Patched by Root

Root has patched CVE-2026-41481 in the rootio-langchain-text-splitters package for Root:PyPI. Multiple fixed versions available...

ROOT-APP-PYPI-CVE-2026-40087 CVE-2026-40087 in rootio-langchain-core - Patched by Root

Root has patched CVE-2026-40087 in the rootio-langchain-core package for Root:PyPI. Multiple fixed versions available...

ROOT-APP-PYPI-CVE-2025-6985 CVE-2025-6985 in rootio-langchain-text-splitters - Patched by Root

Root has patched CVE-2025-6985 in the rootio-langchain-text-splitters package for Root:PyPI. Multiple fixed versions available...

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...

CVE-2026-45134

LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to LangSmith SDK Python 0.8.0 and JS/TS 0.6.0, the LangSmith SDK's prompt pull methods pullprompt / pullpromptcommit in Python, pullPrompt / pullPromptCommit in JS/TS fetch and deserialize prompt manifests from...

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...

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...

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...

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...

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...

CVE-2026-44843

LangChain CVE-2026-44843 affects LangChain-core runtimes prior to 0.3.85 and 1.3.3, which use older code paths with broad object allowlists that can revive trusted LangChain-serializable objects via load()/loads() calls. This may let attacker-controlled serialized constructor dictionaries instant...

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...

LangChain 代码问题漏洞

LangChain is an open-source framework developed by LangChain for creating applications powered by large language models LLMs. Versions of LangChain prior to 0.3.85 and 1.3.3 contained code vulnerabilities. These vulnerabilities stemmed from the use of an overly broad object white-list for...

Security Bulletin: IBM Watson Speech Services Cartridge is vulnerable to a Server-Side Request Forgery in LangChain [CVE-2026-26013]

Summary IBM Watson Speech Services Cartridge is vulnerable to a Server-Side Request Forgery in LangChain, due to a faulty method that fetches arbitrary imageurl values without validation when computing token counts for vision-enabled models. CVE-2026-26013. LangChain is used in our speech runtime...

Security Bulletin: IBM Watson Speech Services Cartridge is vulnerable to a path traversal in LangChain [CVE-2026-34070]

Summary IBM Watson Speech Services Cartridge is vulnerable to a path traversal in LangChain, due to multiple functions in langchaincore.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection...