LangChain 安全漏洞

LangChain is an open-source framework developed by LangChain for creating applications powered by large language models LLMs. Versions of LangChain prior to 1.2.22 contained security vulnerabilities. These vulnerabilities stemmed from multiple functions in langchaincore.promptsloading that read...

LangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functions

Summary Multiple functions in langchaincore.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to loadprompt or loadpromptfromconfig...

Directory Traversal

Overview langchain-core is a Building applications with LLMs through composability Affected versions of this package are vulnerable to Directory Traversal via the loadprompt, loadpromptfromconfig, or .save methods on prompt classes. An attacker can access arbitrary files on the host filesystem by...

GHSA-QH6H-P6C9-FF54 LangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functions

Summary Multiple functions in langchaincore.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to loadprompt or loadpromptfromconfig...

LangChain, LangGraph Flaws Expose Files, Secrets, Databases in Widely Used AI Frameworks

Cybersecurity researchers have disclosed three security vulnerabilities impacting LangChain and LangGraph that, if successfully exploited, could expose filesystem data, environment secrets, and conversation history. Both LangChain and LangGraph are open-source frameworks that are used to build...

PT-2026-28599

Name of the Vulnerable Software and Affected Versions LangChain versions prior to 1.2.22 Description Multiple functions within langchain core.prompts.loading read files from paths embedded in deserialized configuration dictionaries without validating against absolute path injection or directory...

Exploit for CVE-2026-34070

I Found a Path Traversal Bug in LangChain That Could Leak Your...

Security Bulletin: IBM watsonx.data integration has several vulnerabilities due to open source packages (CVE-2018-20225, CVE-2025-6985, CVE-2025-54368)

Summary Open source packages are used as part of the overall processing in IBM watsonx.data integration. Vulnerability Details CVEID:CVE-2018-20225 DESCRIPTION: An issue was discovered in pip all versions because it installs the version with the highest version number, even if the user had intend...

Security Bulletin: IBM Rhapsody Systems Engineering is using langchain-0.3.30 which is vulnerable to CVE-2025-68665

Summary A security vulnerability was identified in the Langchain OSS package used in our product. The issue has been resolved by removing the vulnerable package and all LangChain-related dependencies from the codebase. Vulnerability Details CVEID:CVE-2025-68665 DESCRIPTION: LangChain is a framewo...

From Storage to Steering: Memory Control Flow Attacks on LLM Agents

Modern agentic systems allow Large Language Model LLM agents to tackle complex tasks through extensive tool usage, forming structured control flows of tool selection and execution. Existing security analyses often treat these control flows as ephemeral, one-off sessions, overlooking the persisten...

CVE-2026-25750

Langchain Helm Charts are Helm charts for deploying Langchain applications on Kubernetes. Prior to langchain-ai/helm version 0.12.71, a URL parameter injection vulnerability existed in LangSmith Studio that could allow unauthorized access to user accounts through stolen authentication tokens. The...

Langchain Helm Charts 注入漏洞

Langchain Helm Charts is a Kubernetes Helm chart library developed by LangChain for deploying Langchain applications. Versions of Langchain Helm Charts prior to 0.12.71 contained a injection vulnerability. This vulnerability stemmed from URL parameter injections in LangSmith Studio, which could...

LangChain LangGraph BaseCache Deserialization of Untrusted Data Remote Code Execution Vulnerability

This vulnerability allows remote attackers to execute arbitrary code on affected installations of LangChain LangGraph. Authentication is not required to exploit this vulnerability. The specific flaw exists within the BaseCache class. The issue results from the lack of proper validation of...

Exploit for Server-Side Request Forgery in Langchain

Yasa-CVE-20...

Security Bulletin: IBM Watson Speech Services Cartridge is vulnerable to a template injection vulnerability in LangChain [CVE-2025-65106]

Summary BM Watson Speech Services Cartridge is vulnerable to a template injection vulnerability in LangChain, due to a defect existing in LangChain's prompt template system that allows attackers to access Python object internals through template syntax CVE-2025-65106. LangChain is used in our...

Security Bulletin: Investigation Assistant App for IBM QRadar SIEM is vulnerable to using components with known vulnerabilities

Summary The product includes vulnerable components e.g., framework libraries that could be identified and exploited with automated tools. Investigation Assistant App for IBM QRadar SIEM has addressed the applicable CVEs in an update. Vulnerability Details CVEID:CVE-2025-66221 DESCRIPTION: Werkzeu...

Server-side Request Forgery (SSRF)

Overview @langchain/community is a Third-party integrations for LangChain.js Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via the RecursiveUrlLoader class. An attacker can access internal network resources or sensitive cloud metadata by supplying a public U...

EUVD-2026-8697

LangChain Community: redirect chaining can lead to SSRF bypass via RecursiveUrlLoader...

LangChain Community: redirect chaining can lead to SSRF bypass via RecursiveUrlLoader

Summary A redirect-based Server-Side Request Forgery SSRF bypass exists in RecursiveUrlLoader in @langchain/community. The loader validates the initial URL but allows the underlying fetch to follow redirects automatically, which permits a transition from a safe public URL to an internal or metada...

GHSA-MPHV-75CG-56WG LangChain Community: redirect chaining can lead to SSRF bypass via RecursiveUrlLoader

Summary A redirect-based Server-Side Request Forgery SSRF bypass exists in RecursiveUrlLoader in @langchain/community. The loader validates the initial URL but allows the underlying fetch to follow redirects automatically, which permits a transition from a safe public URL to an internal or metada...