CVE-2024-46946Public exploitNetwork attack vector

Arbitrary code execution via evaluated symbolic expressions

Published Sep 19, 2024 · Updated Sep 19, 2024

Eval injection in LangChain Experimental 0.1.17 through 0.3.0 allows remote attackers to execute arbitrary code through LLMSymbolicMathChain. LLMSymbolicMathChain passes the model-produced expression to sympy.sympify with evaluation enabled, allowing Python directives to reach eval without neutralization. Exploitation requires an application to expose the chain to attacker-influenced prompts, and successful code runs with the application process's privileges.

CVSS severity9.8
Critical
EPSS probability1.39%
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

Eval injection in LangChain Experimental 0.1.17 through 0.3.0 allows remote attackers to execute arbitrary code through LLMSymbolicMathChain. LLMSymbolicMathChain passes the model-produced expression to sympy.sympify with evaluation enabled, allowing Python directives to reach eval without neutralization. Exploitation requires an application to expose the chain to attacker-influenced prompts, and successful code runs with the application process's privileges.

The record

CVE
CVE-2024-46946
Published
Sep 19, 2024
Updated
Sep 19, 2024
Vendor
LangChain
Product
LangChain Experimental
Classifications
CWE-20, T1059.006
Attack vector
network
Privileges
unauthenticated

Timeline

How it unfolded

  1. Sep 19, 2024CVE publishedPublication date reported by the CVE source.
  2. Sep 19, 2024Record 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?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=0.1.17 <=0.3.0

What conditions does exploitation require?

Attack vectornetwork
Required privilegesunauthenticated

What is affected?

LangChain · LangChain Experimentalversion=0.1.17 <=0.3.0

Published CVSS scores

9.8CISA-ADPCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

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-20Improper Input Validation
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