PT-2025-47809

Name of the Vulnerable Software and Affected Versions LangChain versions 0.3.79 and prior LangChain versions 1.0.0 through 1.0.6 Description LangChain is a framework used for building agents and applications powered by Large Language Models LLMs. A template injection issue exists in the prompt...

@ai-sdk/angular (>=1.1.0-beta.0 <=1.1.0-beta.28), @ai-sdk/langchain (>=1.1.0-beta.0 <=1.1.0-beta.28) +5 more potentially affected by CVE-2025-48985 via ai (>=5.1.0-beta.0 <=5.1.0-beta.8)

ai NPM version =5.1.0-beta.0, =1.1.0-beta.0, =1.1.0-beta.0, =1.1.0-beta.0, =2.1.0-beta.0, =1.1.0-beta.0, =3.1.0-beta.0, =2.1.0-beta.0, =2.1.0-beta.28 Source cves: CVE-2025-48985 Source advisory: SNYK:JS-AI-13863465...

Do robots dream of secure networking? Teaching cybersecurity to AI systems

This blog explores how to equip autonomous AI agents with cybersecurity knowledge, enabling them to make informed decisions about internet safety, such as identifying trustworthy links and websites. It demonstrates a proof of concept using LangChain and OpenAI, integrated with the Cisco Umbrella...

deepagents (=0.0.12rc3), gradient-adk (>=0.0.3 <=0.1.9) +2 more potentially affected by CVE-2025-64439 via langgraph (>=1.0.0 <=1.0.0a4)

langgraph PYPI version =1.0.0, =0.0.3, =0.1.9 - langchain =1.0.0a10 - novachain =0.1.0 Source cves: CVE-2025-64439 Source advisory: SNYK:PYTHON-LANGGRAPH-13843663...

CVE-2025-8709

CVE-2025-8709 affects langgraph-checkpoint-sqlite 2.0.10 in LangGraph’s SQLite store. The root cause is improper string concatenation of filter keys in _get_filter_condition(), allowing SQL injection via filter parameters and potentially exposing all documents and sensitive fields (e.g., password...

CVE-2025-8709 SQL Injection in langchain-ai/langchain

A SQL injection vulnerability exists in the langchain-ai/langchain repository, specifically in the LangGraph's SQLite store implementation. The affected version is langgraph-checkpoint-sqlite 2.0.10. The vulnerability arises from improper handling of filter operators $eq, $ne, $gt, $lt, $gte, $lt...

langchainlanggraph-checkpoint-sqlite SQL注入漏洞

langchainlanggraph-checkpoint-sqlite is an open source database connectivity Python library from LangChain. An SQL injection vulnerability exists in langchainlanggraph-checkpoint-sqlite version 2.0.10, which stems from improper handling of the filter operator and could lead to an SQL injection...

XML External Entity (XXE)

langchaincommunity is vulnerable to XML External Entity XXE. The vulnerability is due to insecure XML parsing in the EverNoteLoader component that uses etree.iterparse without disabling external entity references, which allows an attacker to craft a malicious XML payload to access sensitive local...

CVE-2025-6985 vulnerabilities

Vulnerabilities for packages: py3-langchain-text-splitters, open-webui...

GHSA-M42M-M8CR-8M58 vulnerabilities

Vulnerabilities for packages: py3-langchain-text-splitters, open-webui...

CVE-2025-6985 vulnerabilities

Vulnerabilities for packages: open-webui, py3-langchain-text-splitters...

GHSA-M42M-M8CR-8M58 vulnerabilities

Vulnerabilities for packages: open-webui, py3-langchain-text-splitters...

a2a-client-handler (=0.1.0), aa-rag (>=0.1.0 <=0.4.3) +1316 more potentially affected by CVE-2025-6985 via langchain-text-splitters (>=0.0.1 <=0.3.8)

langchain-text-splitters PYPI version =0.0.1, =0.1.0, =0.1.3, =0.1.0, =0.1.0b0, =0.0.1, =4.8.2, =0.0.1a1, =0.1.0, =0.1.0, =1.0.0rc1, =3.2.0, =0.1.0, =0.1.3 and more Source cves: CVE-2025-6985 Source advisory: OSV:GHSA-M42M-M8CR-8M58...

LangChain Text Splitters is vulnerable to XML External Entity (XXE) attacks due to unsafe XSLT parsing

The HTMLSectionSplitter class in langchain-text-splitters is vulnerable to XML External Entity XXE attacks due to unsafe XSLT parsing. This vulnerability arises because the class allows the use of arbitrary XSLT stylesheets, which are parsed using lxml.etree.parse and lxml.etree.XSLT without any...

GHSA-M42M-M8CR-8M58 LangChain Text Splitters is vulnerable to XML External Entity (XXE) attacks due to unsafe XSLT parsing

The HTMLSectionSplitter class in langchain-text-splitters is vulnerable to XML External Entity XXE attacks due to unsafe XSLT parsing. This vulnerability arises because the class allows the use of arbitrary XSLT stylesheets, which are parsed using lxml.etree.parse and lxml.etree.XSLT without any...

CVE-2025-6985

The HTMLSectionSplitter class in langchain-text-splitters version 0.3.8 is vulnerable to XML External Entity XXE attacks due to unsafe XSLT parsing. This vulnerability arises because the class allows the use of arbitrary XSLT stylesheets, which are parsed using lxml.etree.parse and lxml.etree.XSL...

CVE-2025-6985

The CVE-2025-6985 entry concerns LangChain Text Splitters (langchain-text-splitters) v0.3.8, with an XML External Entity (XXE) risk due to unsafe XSLT parsing. The connected docs explain that arbitrary XSLT stylesheets are parsed using lxml.etree.parse() and lxml.etree.XSLT() without hardening, a...

CVE-2025-6985 XXE Vulnerability in langchain-ai/langchain

The HTMLSectionSplitter class in langchain-text-splitters version 0.3.8 is vulnerable to XML External Entity XXE attacks due to unsafe XSLT parsing. This vulnerability arises because the class allows the use of arbitrary XSLT stylesheets, which are parsed using lxml.etree.parse and lxml.etree.XSL...

CVE-2025-6985 XXE Vulnerability in langchain-ai/langchain

The HTMLSectionSplitter class in langchain-text-splitters version 0.3.8 is vulnerable to XML External Entity XXE attacks due to unsafe XSLT parsing. This vulnerability arises because the class allows the use of arbitrary XSLT stylesheets, which are parsed using lxml.etree.parse and lxml.etree.XSL...

langchain-text-splitters 代码问题漏洞

langchain-text-splitters is a Python package open-sourced by LangChain. A code issue vulnerability exists in langchain-text-splitters version 0.3.8, which stems from the HTMLSectionSplitter class allowing the use of arbitrary XSLT stylesheets, which could lead to an XML External Entity Attack,...