CVE-2023-29374Public exploitNetwork attack vector

Arbitrary code execution via model-generated Python

Published Apr 5, 2023 · Updated Feb 12, 2025

Code injection in LLMMathChain in LangChain through 0.0.131 allows remote attackers to execute arbitrary code through crafted prompts. The chain submits user-influenced text to the language model, extracts the generated Python expression, and passes it directly to exec without restricting the code. Exploitation requires an application to expose LLMMathChain to attacker-controlled prompts or untrusted model output, after which code runs with the hosting Python process's permissions.

CVSS severity9.3
Critical
EPSS probability39.65%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Code injection in LLMMathChain in LangChain through 0.0.131 allows remote attackers to execute arbitrary code through crafted prompts. The chain submits user-influenced text to the language model, extracts the generated Python expression, and passes it directly to exec without restricting the code. Exploitation requires an application to expose LLMMathChain to attacker-controlled prompts or untrusted model output, after which code runs with the hosting Python process's permissions.

The record

CVE
CVE-2023-29374
Published
Apr 5, 2023
Updated
Feb 12, 2025
Vendor
Unknown vendor
Product
Unknown product
Classifications
CWE-94, CWE-74, T1059.006
Attack vector
network
Privileges
unauthenticated

Timeline

How it unfolded

  1. Apr 5, 2023CVE publishedPublication date reported by the CVE source.
  2. Feb 12, 2025Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Affected buildAffected product and version details are unavailable.

What conditions does exploitation require?

Attack vectornetwork
Required privilegesunauthenticated

What is affected?

Affected products and versions are unavailable in this record.

Published CVSS scores

9.3GitHub Advisory DatabaseCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesunauthenticated
Known exploitationUnconfirmed
Public exploitPublished

Weakness, pattern, technique

CWE-94Improper Control of Generation of Code ('Code Injection')
CWE-74Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')
T1059.006Command and Scripting Interpreter: Python

Public exploit references

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo