CVE-2024-46946: Langchain experimental LangChain Experimental Eval Injection Vulnerability Vulnerability

CRITICAL
Advisory Identifier: GHSA-p2qj-r53j-h3xj
Share
CVSS 9.8
CWE-95
Published
Advisory Summary

CVE-2024-46946 is a CRITICAL (CVSS 9.8) langchain experimental eval injection vulnerability vulnerability (CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection')) affecting Langchain experimental libraries in the PyPI ecosystem. The issue involves langchain experimental eval injection vulnerability. Remediation is available in the latest vendor maintenance releases.

CVE-2024-46946 at a Glance

CVE Identifier CVE-2024-46946
GHSA Identifier GHSA-p2qj-r53j-h3xj
Severity CRITICAL
CVSS v3.1 Base Score 9.8
CWE Classification CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection')
Affected Product Langchain experimental
Package Ecosystem PyPI
Published Date
Last Updated

Security Impact

CVSS: 9.8

The security impact metrics below are parsed directly from the CVSS v3.1 vector string (CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H).

Attack Vector Network (AV:N)
Attack Complexity Low (AC:L)
Privileges Required None (PR:N)
User Interaction None (UI:N)
Scope Unchanged (S:U)
Confidentiality High (C:H)
Integrity High (I:H)
Availability High (A:H)

How to Fix CVE-2024-46946

To remediate this vulnerability, upgrade all affected Langchain experimental dependencies to a patched release. Both direct and transitive dependencies should be checked, as frameworks or security libraries may pull in vulnerable versions transitively.

langchain-experimental fixed: Latest secure release 
pip install langchain-experimental>=Latest secure release
Verify Direct and Transitive Dependencies

Run the following command in your project directory to verify that all resolved dependencies use the patched release: 

pip show langchain-experimental

How to Check if You Are Affected

To determine whether your Python environment is affected by CVE-2024-46946, inspect your installed packages using pip:

pip show langchain-experimental

Analyze the terminal output to locate any version of Langchain experimental in your dependency tree. If any resolved version matches the vulnerable ranges listed in the table below (for example, versions earlier than the patched release), your application is affected.

Note: The pip show langchain-experimental command checks currently installed packages in your active Python environment.

Technical Details

Vulnerability Mechanism & Technical Analysis

This vulnerability is classified under CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection'), where the product receives input from an upstream component, but it does not neutralize or incorrectly neutralizes code syntax before using the input in a dynamic evaluation call (e.g. "eval"). In Langchain experimental, software state validation or input boundaries are circumvented during processing. Review the official source advisory statement below for specific affected components, classes, and reproduction details.

Source Advisory Statement

langchain_experimental (aka LangChain Experimental) 0.1.17 through 0.3.0 for LangChain allows attackers to execute arbitrary code through sympy.sympify (which uses eval) in LLMSymbolicMathChain. LLMSymbolicMathChain was introduced in fcccde406dd9e9b05fc9babcbeb9ff527b0ec0c6 (2023-10-05).

CVE-2024-46946 Affected Langchain experimental Versions

1 component(s)
Product / Package Ecosystem Affected Versions Fixed Version
langchain-experimental
pypi/langchain-experimental
PyPI
≥ 0.1.17
≤ 0.3.0

References

NVD — CVE-2024-46946 NVD
https://nvd.nist.gov/vuln/detail/CVE-2024-46946
docs.sympy.org/latest/modules/code... WEB
https://docs.sympy.org/latest/modules/codegen.html
Langchain experimental Source Repository REPOSITORY
https://gist.github.com/12end/68c0c58d2564ef4141bccd4651480820#file-cve-2024-46946-txt
Langchain experimental Source Repository REPOSITORY
https://github.com/langchain-ai/langchain
Langchain experimental Release RELEASE
https://github.com/langchain-ai/langchain/releases/tag/langchain-experimental%3D%3D0.3.0

Frequently Asked Questions

What is CVE-2024-46946?
CVE-2024-46946 is a security vulnerability in Langchain experimental involving LangChain Experimental Eval Injection vulnerability under CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection').
Which Langchain experimental versions are affected?
Affected versions include releases prior to current release patches across affected packages: langchain-experimental.
What version fixes CVE-2024-46946?
Upgrading to current release patches (or the latest patched release for your respective branch) resolves the vulnerability.
Is langchain-experimental affected?
Yes, langchain-experimental is affected in releases prior to Latest secure release. Upgrade your dependency to Latest secure release or later.
What is the CVSS score of CVE-2024-46946?
CVE-2024-46946 has a CVSS v3.1 base score of 9.8 (CRITICAL) with vector string CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.
What CWE is associated with CVE-2024-46946?
CVE-2024-46946 is classified under CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection') (The product receives input from an upstream component, but it does not neutralize or incorrectly neutralizes code syntax before using the input in a dynamic evaluation call (e.g. "eval").).
How can I check PyPI dependencies for CVE-2024-46946?
Run the dependency tree command: 'pip show langchain-experimental'. This command lists direct and transitive dependencies in your build configuration so you can verify if a vulnerable version is resolved.
Machine-readable OSV JSON OSV v1.5 Schema
Normalized schema output
View Raw JSON 
{
  "schema_version" : "1.4.0",
  "id" : "GHSA-p2qj-r53j-h3xj",
  "modified" : "2024-09-19T18:23:47Z",
  "published" : "2024-09-19T06:31:36Z",
  "aliases" : [ "CVE-2024-46946" ],
  "summary" : "LangChain Experimental Eval Injection vulnerability",
  "details" : "langchain_experimental (aka LangChain Experimental) 0.1.17 through 0.3.0 for LangChain allows attackers to execute arbitrary code through sympy.sympify (which uses eval) in LLMSymbolicMathChain. LLMSymbolicMathChain was introduced in fcccde406dd9e9b05fc9babcbeb9ff527b0ec0c6 (2023-10-05).",
  "severity" : [ {
    "type" : "CVSS_V3",
    "score" : "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H"
  }, {
    "type" : "CVSS_V4",
    "score" : "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "langchain-experimental"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0.1.17"
      }, {
        "last_affected" : "0.3.0"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "ADVISORY",
    "url" : "https://nvd.nist.gov/vuln/detail/CVE-2024-46946"
  }, {
    "type" : "WEB",
    "url" : "https://docs.sympy.org/latest/modules/codegen.html"
  }, {
    "type" : "WEB",
    "url" : "https://gist.github.com/12end/68c0c58d2564ef4141bccd4651480820#file-cve-2024-46946-txt"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/langchain-ai/langchain"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/langchain-ai/langchain/releases/tag/langchain-experimental%3D%3D0.3.0"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-95" ],
    "severity" : "CRITICAL",
    "github_reviewed" : true,
    "github_reviewed_at" : "2024-09-19T18:23:47Z",
    "nvd_published_at" : "2024-09-19T05:15:11Z"
  }
}