CVE-2023-44467
9.8 · CRITICALOverview
CVE-2023-44467 is a critical-severity vulnerability affecting langchain langchain_experimental. It was published on October 9, 2023 and has a CVSS 3.1 base score of 9.8 (CRITICAL).
This vulnerability has a CVSS 3.1 base score of 9.8, rated CRITICAL. It can be exploited remotely over the network. No authentication or special privileges are required for exploitation.
Technical Description
langchain_experimental (aka LangChain Experimental) in LangChain before 0.0.306 allows an attacker to bypass the CVE-2023-36258 fix and execute arbitrary code via __import__ in Python code, which is not prohibited by pal_chain/base.py.
Remediation
Check the references section for vendor advisories and patches from langchain. Update langchain_experimental to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.
Affected Products
| Vendor | Product | Versions | Status |
|---|
Frequently Asked Questions
What is CVE-2023-44467?
CVE-2023-44467 is a critical-severity vulnerability affecting langchain langchain_experimental. It was published on October 9, 2023 and has a CVSS 3.1 base score of 9.8 (CRITICAL).
How severe is CVE-2023-44467?
This vulnerability has a CVSS 3.1 base score of 9.8, rated CRITICAL. It can be exploited remotely over the network. No authentication or special privileges are required for exploitation.
How do I fix or remediate CVE-2023-44467?
Check the references section for vendor advisories and patches from langchain. Update langchain_experimental to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.
How can CyberStrike help with CVE-2023-44467?
CyberStrike's AI-powered security agents can automatically detect CVE-2023-44467 across your infrastructure using autonomous pentesting, DAST scanning, and HackBrowser. The platform continuously monitors for known vulnerabilities and provides actionable remediation guidance prioritized by real-world exploitability.
How CyberStrike Helps
AI agents map your attack surface to find vulnerabilities like this one.
Automated penetration testing that runs continuously, not just quarterly.
AI-driven PR review catches vulnerable dependencies before they ship.
Browser-based exploitation validates findings with real proof-of-concept.
Related CRITICAL CVEs from 2023
View all →Out-of-bounds write vulnerability in Remote Desktop Functionality in Synology VPN Plus Server before
Due to improper input sanitization of user-controlled input in SAP BusinessObjects Business Intellig
InHand Networks InRouter 302, prior to version IR302 V3.5.56, and InRouter 615, prior to version In
InHand Networks InRouter 302, prior to version IR302 V3.5.56, and InRouter 615, prior to version In
Sewio’s Real-Time Location System (RTLS) Studio version 2.0.0 up to and including version 2.6.2 cont
Baicells Nova 227, Nova 233, and Nova 243 LTE TDD eNodeB devices with firmware through RTS/RTD 3.7.1
Dompdf is an HTML to PDF converter. The URI validation on dompdf 2.0.1 can be bypassed on SVG parsin
IBM Tivoli Workload Scheduler 9.4, 9.5, and 10.1 is vulnerable to an XML External Entity Injection (
Dompdf is an HTML to PDF converter written in php. Due to the difference in the attribute parser of
A vulnerability has been identified in COMOS V10.2 (All versions), COMOS V10.3.3.1 (All versions < V
Due to improper artibute filtering in the sequalize js library, can a attacker peform SQL injections
Sequelize is a Node.js ORM tool. In versions prior to 6.19.1 a SQL injection exploit exists related