Home > Vulnerability Database > CVE-2023-29374

Mend.io Vulnerability Database

New vulnerability? Tell us about it!

CVE-2023-29374

Good to know:

Date: April 4, 2023

In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.

Language: Python

Severity Score

9.8

Related Resources (8)

Url: https://nvd.nist.gov/vuln/detail/CVE-2023-29374

Url: https://github.com/hwchase17/langchain/issues/814

Url: https://github.com/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2023-18.yaml

Url: https://twitter.com/rharang/status/1641899743608463365/photo/1

Url: https://github.com/hwchase17/langchain/pull/1119

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

Url: https://github.com/hwchase17/langchain/issues/1026

Url: https://www.mend.io/vulnerability-database/CVE-2023-29374

Severity Score

9.8

Weakness Type (CWE)

Improper Control of Generation of Code ('Code Injection')

CWE-94

Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')

CWE-74

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