Is CVE-2023-29374 actively exploited?

No active exploitation of CVE-2023-29374 has been confirmed so far. Continue monitoring, as exploit status can change.

Can CVE-2023-29374 be exploited remotely?

Yes. CVE-2023-29374 is exploitable remotely over the network (CVSS attack vector: Network).

What is the CVSS score of CVE-2023-29374?

CVE-2023-29374 has a CVSS score of 9.8 (CRITICAL).

HOME VULNERABILITIESCVE-2023-29374

CRITICAL

CVE-2023-29374

CWE-74Published: April 5, 2023· Updated: Jun 17, 2026

9.8

CVSS v3.1

Official Description

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

NVD Source

Risk Analysis

LangChain's LLMMathChain is susceptible to prompt injection, enabling arbitrary code execution via the Python exec method. This critical vulnerability is remotely exploitable and carries a CVSS score of 9.8.

No public exploit is known, and the vulnerability is not in the CISA KEV catalog.

Recommended Action

Upgrade to a patched version of LangChain that addresses the prompt injection flaw.

Generated by the CTIWATCH analysis pipeline from this CVE's metadata (CVSS, EPSS, KEV status, exploit intelligence). Verify against vendor advisories before acting.

Technical Analysis

CVE-2023-29374 can be exploited remotely over the network without requiring physical or adjacent access, significantly expanding the attack surface for threat actors.

The vulnerability requires no privileges and no user interaction, making it a prime target for automated exploitation campaigns and worm-like propagation.

A successful exploit results in complete confidentiality breach (data exposure), full integrity compromise (data manipulation), availability disruption (denial of service), with a CVSS base score of 9.8.