# CVE-2024-28088: LangChain directory traversal vulnerability

Source: https://junglewise.ai/threats/cve-2024-28088-langchain-directory-traversal-vulnerability  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2024-03-04  
License: CC BY 4.0 with a link back

CVE-2024-28088 · Severity: info · Published 2024-03-04

LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a load_chain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure of an API key for a large language model online service, or remote code execution. (A patch is available as of release 0.1.29 of langchain-core.)

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

## Quick answers

**Is CVE-2024-28088 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2024-28088 being exploited in the wild.

**How severe is CVE-2024-28088?** Informational severity, published 4 March 2024.

**Which products and versions are affected?** langchain (PyPI) ECOSYSTEM:introduced=0,fixed=0.0.339, ECOSYSTEM:introduced=0,fixed=0.1.11; langchain-core (PyPI) ECOSYSTEM:introduced=0,fixed=0.1.11, ECOSYSTEM:introduced=0,fixed=0.1.30.

**Is there a fix for CVE-2024-28088?** Yes. langchain (PyPI): upgrade to 0.0.339, 0.1.11 or later; langchain-core (PyPI): upgrade to 0.1.11, 0.1.30 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**Am I affected by CVE-2024-28088?** Check whether you run langchain (PyPI) or langchain-core (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 0.0.339, 0.1.11 or later

  ```sh
  pip install "langchain>=0.1.11"
  ```

- langchain-core (PyPI): upgrade to 0.1.11, 0.1.30 or later

  ```sh
  pip install "langchain-core>=0.1.30"
  ```


## Affected products

- langchain (PyPI) ECOSYSTEM:introduced=0,fixed=0.0.339, ECOSYSTEM:introduced=0,fixed=0.1.11
- langchain-core (PyPI) ECOSYSTEM:introduced=0,fixed=0.1.11, ECOSYSTEM:introduced=0,fixed=0.1.30

## Identifiers

- CVE-2024-28088
- GHSA-h59x-p739-982c
- PYSEC-2024-43
- PYSEC-2024-45

## Related threats

- [PYSEC-2026-2562 - LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages](https://junglewise.ai/threats/cve-2026-26013-langchain-chatopenai-server-side-request-forgery-via-image-token)
- [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-2026-1517 - langchain-core allows unauthorized users to read arbitrary files from the host file system](https://junglewise.ai/threats/cve-2024-10940-langchain-core-allows-unauthorized-users-to-read-arbitrary-files)
- [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)