AI and data stack advisories

Severe, 6 weeks1498Projects326

1498 severe, 6 weeks · 326 projects

LangChainGHSA-f2jm-rw3h-6phg

LangChain pickle deserialization of untrusted data

LangChain

CVE-2024-5998 · Published Sep 17, 2024 · updated Jul 13, 2026

High5.2
Fix: upgrade to 0.2.4 or later
GitHub advisory

A vulnerability in the FAISS.deserialize_from_bytes function of langchain-ai/langchain allows for pickle deserialization of untrusted data. This can lead to the execution of arbitrary commands via the os.system function. The issue affects versions prior to 0.2.4.

Affected versions

PackageAffectedFixed in
langchain-community
PyPI
< 0.2.40.2.4
Details and references
CVSS 3.1
CVSS:3.1/AV:P/AC:L/PR:L/UI:R/S:U/C:H/I:L/A:L
Severity from
GitHub (reviewed advisory)
Weakness
CWE-502
Also known as
CVE-2024-5998, PYSEC-2024-323, PYSEC-2026-1514

More LangChain advisories

All LangChain
Low 4.9Oct 29, 2024@langchain/community SQL Injection vulnerabilityCVE-2024-7042fixed in 0.3.3Medium 6.5Oct 29, 2024Langchain Path Traversal vulnerabilityCVE-2024-7774fixed in 0.2.19Low 4.9Oct 29, 2024Langchain SQL Injection vulnerabilityCVE-2024-8309fixed in 0.2.0 +1Critical 9.8Sep 19, 2024LangChain Experimental Eval Injection vulnerabilityCVE-2024-46946no fix yetCritical 8.5Jul 15, 2024langchain-experimental vulnerable to Arbitrary Code ExecutionCVE-2024-21513fixed in 0.0.21High 7.8Jun 16, 2024langchain_experimental Code Execution via Python REPL accessCVE-2024-38459fixed in 0.0.61