# CVE-2023-36188: LangChain remote code execution in PALChain Python exec method

Source: https://junglewise.ai/threats/cve-2023-36188-langchain-remote-code-execution-in-palchain-python-exec-method  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2023-07-06. Updated: 2026-07-06  
License: CC BY 4.0 with a link back

CVE-2023-36188 · Severity: critical · CVSS 9.8 · Published 2023-07-06

LangChain, a popular framework for building applications with large language models, is vulnerable to a critical security flaw. An attacker can remotely execute malicious code on the system running the software by exploiting how it handles certain Python execution parameters. This could lead to a full system takeover, data theft, or disruption of services.

Technologies: [langchain (PyPI)](https://junglewise.ai/threats/technologies/langchain). Vendors: [PyPI](https://junglewise.ai/threats/vendors/pypi).

## Quick answers

**Is CVE-2023-36188 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2023-36188 being exploited in the wild.

**How severe is CVE-2023-36188?** Critical severity, with a CVSS score of 9.8, published 6 July 2023.

**Which products and versions are affected?** langchain (PyPI) < 0.0.247, ECOSYSTEM:introduced=0,fixed=0.0.247.

**Is there a fix for CVE-2023-36188?** Yes. langchain (PyPI): upgrade to 0.0.247 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2023-36188 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2023-36188?** Check whether you run langchain (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- langchain (PyPI): upgrade to 0.0.247 or later

  ```sh
  pip install "langchain>=0.0.247"
  ```


## Technical details

A remote code execution (RCE) vulnerability exists in LangChain due to improper neutralization of special elements used in downstream components (CWE-74). The flaw is located within the PALChain parameter of the Python exec method, where externally-influenced input is insufficiently sanitized before being executed. A remote, unauthenticated attacker can exploit this by providing crafted input that triggers arbitrary command execution on the host system. The vulnerability is addressed in version 0.0.247.

## Affected products

- langchain-ai langchain < 0.0.247

## Identifiers

- CVE-2023-36188
- GHSA-57fc-8q82-gfp3
- PYSEC-2023-109

## Timeline

- 2023-07-06: advisory
- 2023-07-06: disclosed
- 2023-07-06: patched

## References

- [https://api.github.com/users/cookesan](https://api.github.com/users/cookesan)
- [https://github.com/cookesan](https://github.com/cookesan)
- [https://api.github.com/users/cookesan/gists%7B/gist_id%7D](https://api.github.com/users/cookesan/gists%7B/gist_id%7D)
- [https://api.github.com/users/cookesan/repos](https://api.github.com/users/cookesan/repos)
- [https://avatars.githubusercontent.com/u/6601329?v=4](https://avatars.githubusercontent.com/u/6601329?v=4)
- [https://api.github.com/users/cookesan/events%7B/privacy%7D](https://api.github.com/users/cookesan/events%7B/privacy%7D)

## Related threats

- [PYSEC-2026-2561 - Denial of service in langchain-community](https://junglewise.ai/threats/cve-2024-2965-langchain-sitemaploader-denial-of-service-via-infinite-recursion)
- [PYSEC-2026-1507 - Langchain SQL Injection vulnerability](https://junglewise.ai/threats/cve-2024-8309-langchain-sql-injection-vulnerability)
- [PYSEC-2026-1514 - LangChain pickle deserialization of untrusted data](https://junglewise.ai/threats/cve-2024-5998-langchain-pickle-deserialization-of-untrusted-data)
- [PYSEC-2026-1510 - langchain vulnerable to path traversal](https://junglewise.ai/threats/cve-2024-3571-langchain-vulnerable-to-path-traversal)
- [PYSEC-2026-1509 - langchain Server-Side Request Forgery vulnerability](https://junglewise.ai/threats/cve-2024-0243-langchain-server-side-request-forgery-vulnerability)