CVE-2023-29374

State: Published
Severity: 9.8 Critical
Published: Apr 5, 2023
Updated: Feb 12, 2025
Reserved: Apr 5, 2023

Description

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

Scores

CVSS	Score	Vector	Source
3.1	9.8 Critical	CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H	CISA-ADP

Weaknesses

CWE-74 Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')

Affected Products

Product	Versions
n/an/a	n/aAffected

References

https://github.com/hwchase17/langchain/pull/1119
https://github.com/hwchase17/langchain/issues/814
https://twitter.com/rharang/status/1641899743608463365/photo/1
https://github.com/hwchase17/langchain/issues/1026

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.