Home > Vulnerability Database > CVE-2023-36281

Mend.io Vulnerability Database

New vulnerability? Tell us about it!

CVE-2023-36281

Good to know:

Date: August 21, 2023

An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via a JSON file to load_prompt. This is related to __subclasses__ or a template.

Language: Python

Severity Score

9.8

Related Resources (9)

Url: https://nvd.nist.gov/vuln/detail/CVE-2023-36281

Url: https://aisec.today/LangChain-2e6244a313dd46139c5ef28cbcab9e55

Url: https://github.com/langchain-ai/langchain/commit/22abeb9f6cc555591bf8e92b5e328e43aa07ff6c

Url: https://github.com/hwchase17/langchain/issues/4394

Url: https://github.com/langchain-ai/langchain

Url: https://github.com/langchain-ai/langchain/pull/10252

Url: https://github.com/langchain-ai/langchain/releases/tag/v0.0.312

Url: https://github.com/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2023-151.yaml

Url: https://www.mend.io/vulnerability-database/CVE-2023-36281

Severity Score

9.8

Weakness Type (CWE)

Code Injection

CWE-94

Top Fix

Upgrade Version

Upgrade to version langchain - 0.0.312

CVSS v3.1

Base Score:	9.8
Attack Vector (AV):	NETWORK
Attack Complexity (AC):	LOW
Privileges Required (PR):	NONE
User Interaction (UI):	NONE
Scope (S):	UNCHANGED
Confidentiality (C):	HIGH
Integrity (I):	HIGH
Availability (A):	HIGH

Do you need more information?

Contact Us