PT-2026-7475

Name of the Vulnerable Software and Affected Versions LangChain versions prior to 1.2.11 Description LangChain is a framework used for building applications powered by large language models LLMs. A flaw exists in the ChatOpenAI.get num tokens from messages method where it retrieves image URLs...

CVE-2026-26013: Server-Side Request Forgery (SSRF)

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.2.11, the ChatOpenAI.getnumtokensfrommessages method fetches arbitrary imageurl values without validation when computing token counts for vision-enabled models. This allows attackers to trigger Server-Side Reque...

LangChain code-related vulnerabilities

LangChain is an open-source framework developed by LangChain for creating applications powered by large language models LLMs. Versions of LangChain prior to 1.2.11 contained code vulnerabilities. These vulnerabilities stemmed from the ChatOpenAI.getnumtokensfrommessages method, which did not...

Security Bulletin: The IBM Maximo Application Suite AI-Service component uses multiple third-party dependencies that contain vulnerabilities associated with multiple CVEs.

Summary The IBM Maximo Application Suite AI-Service component uses"langchaincore-0.3.29-py3-none-any.whl, langchaincore-0.3.80-py3-none-any.whl, jsonpath-plus-8.1.0.tgz, mlflow-2.19.0-py3-none-any.whl, pg8000-1.31.2-py3-none-any.whl" which are vulnerable to "CVE-2025-68664, CVE-2024-21534,...

Security Bulletin: The IBM Maximo Application Suite AI-Service component uses multiple third-party dependencies that contain vulnerabilities associated with multiple CVEs.

Summary The IBM Maximo Application Suite AI-Service component uses "FlaskCors-4.0.2-py2.py3-none-any.whl, langchaincommunity-0.3.3-py3-none-any.whl, langchaincore-0.3.29-py3-none-any.whl, langchaintextsplitters-0.3.5-py3-none-any.whl, pdfminersix-20250327-py3-none-any.whl,...

Critical: Red Hat Security Advisory: Red Hat OpenShift Lightspeed 1.0.9 security update

Red Hat OpenShift Lightspeed 1.0.9 operand images, which provide security fixes and container updates. Red Hat OpenShift Lightspeed is a generative AI-based virtual assistant integrated into the OpenShift console. It can answer questions related to OpenShift and layered offerings. Security Fixes:...

Case study: Securing AI application supply chains

The rapid adoption of AI applications, including agents, orchestrators, and autonomous workflows, represents a significant shift in how software systems are built and operated. Unlike traditional applications, these systems are active participants in execution. They make decisions, invoke tools,...

Case study: Securing AI application supply chains

The rapid adoption of AI applications, including agents, orchestrators, and autonomous workflows, represents a significant shift in how software systems are built and operated. Unlike traditional applications, these systems are active participants in execution. They make decisions, invoke tools,...

Serialization Injection Vulnerability

LangChain is vulnerable to a Serialization Injection Vulnerability. The vulnerability is due to improper handling of user-controlled objects containing lc keys in the toJSON serialization logic, which allows an attacker to inject crafted data that is mistakenly treated as a trusted LangChain obje...

Serialization Injection Vulnerability

langchaincore is vulnerable to a Serialization Injection Vulnerability. The vulnerability is due to the dumps and dumpd functions not escaping user-controlled dictionaries containing the internal lc key, which allows an attacker to craft malicious input that is interpreted as a trusted LangChain...

centricube-langchain (>=1.2.3, <=1.3.0), centricube-pyautogen (>=0.3.2, <=0.3.3) +5 more potentially affected by CVE-2026-24688 via pypdf (5.6.1)

pypdf PYPI version 5.6.1 is affected by a known vulnerability. The following packages have a transitive dependency on pypdf and may be impacted: - centricube-langchain =1.2.3, =0.3.2, =0.3.0, =0.1.0, =0.0.11, =0.0.3, =0.0.5 Source cves: CVE-2026-24688 Source advisory: OSV:GHSA-2Q4J-M29V-HQ73...

GHSA-C67J-W6G6-Q2CM vulnerabilities

Vulnerabilities for packages: py3-langchain...

CVE-2025-68664 vulnerabilities

Vulnerabilities for packages: py3-langchain...

GHSA-C67J-W6G6-Q2CM vulnerabilities

Vulnerabilities for packages: py3-langchain...

CVE-2025-68664 vulnerabilities

Vulnerabilities for packages: py3-langchain...

Arbitrary File Upload

@n8n/n8n-nodes-langchain is vulnerable to Arbitrary File Upload. The vulnerability is due to improper validation and handling of uploaded files in the Chat Trigger component, which allows an attacker to upload a crafted HTML file and execute arbitrary code on the affected system...

CVE-2024-58340

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service ReDoS vulnerability in the MRKLOutputParser.parse method libs/langchain/langchain/agents/mrkl/outputparser.py. The parser applies a backtracking-prone regular expression when extracting tool actions from...

agent-nexus-cli (>=0.1.0, <=0.1.31), aggregation-agent (>=0.1.2, <=0.1.11) +32 more potentially affected by CVE-2024-58340 via langchain-classic (>=1.0.0, <=1.0.1)

langchain-classic PYPI version =1.0.0, =0.1.0, =0.1.2, =0.1.0, =3.0.3, =3.1.0, =0.0.597, =0.1.0, =0.1.0, =0.1.0, =0.1.0, =0.1.0, =0.1.2, =0.1.9 - hspylib-askai 1.2.19 and more Source cves: CVE-2024-58340 Source advisory: SNYK:PYTHON-LANGCHAINCLASSIC-14914754...

CVE-2024-58340

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service ReDoS vulnerability in the MRKLOutputParser.parse method libs/langchain/langchain/agents/mrkl/outputparser.py. The parser applies a backtracking-prone regular expression when extracting tool actions from...

PYSEC-2026-75

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service ReDoS vulnerability in the MRKLOutputParser.parse method libs/langchain/langchain/agents/mrkl/outputparser.py. The parser applies a backtracking-prone regular expression when extracting tool actions from...