Vulnerabilities in pkg:pypi/langchain-experimental

PACKAGE
Advisory Identifier: GHSA-gjjr-63x4-v8cq
Share
Advisory Summary

CVE-2023-44467 is a CRITICAL (CVSS 9.8) langchain_experimental vulnerable to arbitrary code vulnerability (General Security Weakness) affecting Langchain experimental libraries in the PyPI ecosystem. The issue involves langchain_experimental vulnerable to arbitrary code execution via palchain in the python exec method. Remediation is available in the latest vendor maintenance releases.

5 Known Advisory Record(s)
Package Vulnerability Intelligence

pkg:pypi/langchain-experimental

5 Known Advisory Record(s)

Vulnerability advisories affecting package pkg:pypi/langchain-experimental. Select an advisory below to view technical details or fixes.

Advisory ID CVE / NVD Severity Summary
GHSA-gjjr-63x4-v8cq CVE-2023-44467 CRITICAL langchain_experimental vulnerable to arbitrary code execution via PALChain in the python exec method
GHSA-cgcg-p68q-3w7v CVE-2024-21513 CRITICAL langchain-experimental vulnerable to Arbitrary Code Execution
GHSA-p2qj-r53j-h3xj CVE-2024-46946 CRITICAL LangChain Experimental Eval Injection vulnerability
GHSA-v8vj-cv27-hjv8 CVE-2024-27444 CRITICAL LangChain Experimental vulnerable to arbitrary code execution
GHSA-wmvm-9vqv-5qpp CVE-2024-38459 HIGH langchain_experimental Code Execution via Python REPL access

CVE-2023-44467 at a Glance

CVE Identifier CVE-2023-44467
GHSA Identifier GHSA-gjjr-63x4-v8cq
Severity CRITICAL
CVSS v3.1 Base Score 9.8
CWE Classification General Security Weakness
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-2023-44467

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-2023-44467, 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 General Security Weakness. 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) in LangChain before 0.0.306 allows an attacker to bypass the CVE-2023-36258 fix and execute arbitrary code via __import__ in Python code, which is not prohibited by pal_chain/base.py.

CVE-2023-44467 Affected Langchain experimental Versions

1 component(s)
Product / Package Ecosystem Affected Versions Fixed Version
langchain-experimental
pypi/langchain-experimental
PyPI
≤ 0.0.14

References

NVD — CVE-2023-44467 NVD
https://nvd.nist.gov/vuln/detail/CVE-2023-44467
Langchain experimental Source Repository REPOSITORY
https://github.com/langchain-ai/langchain/pull/11233
Security Fix Commit FIX COMMIT
https://github.com/langchain-ai/langchain/commit/4c97a10bd0d9385cfee234a63b5bd826a295e483
Langchain experimental Source Repository REPOSITORY
https://github.com/langchain-ai/langchain
Langchain experimental Source Repository REPOSITORY
https://github.com/pypa/advisory-database/tree/main/vulns/langchain-experimental/PYSEC-2023-194.yaml
pypi.org/project/langchain-e... WEB
https://pypi.org/project/langchain-experimental/0.0.14

Frequently Asked Questions

What is CVE-2023-44467?
CVE-2023-44467 is a security vulnerability in Langchain experimental involving langchain_experimental vulnerable to arbitrary code execution via PALChain in the python exec method under General Security Weakness.
Which Langchain experimental versions are affected?
Affected versions include releases prior to current release patches across affected packages: langchain-experimental.
What version fixes CVE-2023-44467?
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-2023-44467?
CVE-2023-44467 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-2023-44467?
CVE-2023-44467 is classified under General Security Weakness.
How can I check PyPI dependencies for CVE-2023-44467?
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-gjjr-63x4-v8cq",
  "modified" : "2025-02-24T20:47:26Z",
  "published" : "2023-10-09T21:30:27Z",
  "aliases" : [ "CVE-2023-44467" ],
  "summary" : "langchain_experimental vulnerable to arbitrary code execution via PALChain in the python exec method",
  "details" : "langchain_experimental (aka LangChain Experimental) in LangChain before 0.0.306 allows an attacker to bypass the CVE-2023-36258 fix and execute arbitrary code via __import__ in Python code, which is not prohibited by pal_chain/base.py.",
  "severity" : [ {
    "type" : "CVSS_V3",
    "score" : "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "langchain-experimental"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0"
      }, {
        "last_affected" : "0.0.14"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "ADVISORY",
    "url" : "https://nvd.nist.gov/vuln/detail/CVE-2023-44467"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/langchain-ai/langchain/pull/11233"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/langchain-ai/langchain/commit/4c97a10bd0d9385cfee234a63b5bd826a295e483"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/langchain-ai/langchain"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/pypa/advisory-database/tree/main/vulns/langchain-experimental/PYSEC-2023-194.yaml"
  }, {
    "type" : "WEB",
    "url" : "https://pypi.org/project/langchain-experimental/0.0.14"
  } ],
  "database_specific" : {
    "cwe_ids" : [ ],
    "severity" : "CRITICAL",
    "github_reviewed" : true,
    "github_reviewed_at" : "2023-10-10T21:19:42Z",
    "nvd_published_at" : "2023-10-09T20:15:10Z"
  }
}