Skip to content
LangChainGHSA-f2jm-rw3h-6phg

LangChain pickle deserialization of untrusted data

High5.2CVE-2024-5998 · Published Sep 17, 2024 · updated Jul 13, 2026

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.

GitHub advisory

Affected versions

PackageAffectedFixed in
langchain-community
PyPI
< 0.2.40.2.4
Details and references

More LangChain advisories

All LangChain
Advisory
@langchain/community SQL Injection vulnerability
Low4.9Oct 29, 2024
Langchain Path Traversal vulnerability
Medium6.5Oct 29, 2024
Langchain SQL Injection vulnerability
Low4.9Oct 29, 2024
LangChain Experimental Eval Injection vulnerability
Critical9.8Sep 19, 2024
langchain-experimental vulnerable to Arbitrary Code Execution
Critical8.5Jul 15, 2024
langchain_experimental Code Execution via Python REPL access
High7.8Jun 16, 2024

Critical advisories by email

Wednesdays: the week’s critical and high advisories in the AI and data stack, with the fixed versions. Only in weeks that have some.

Double opt-in. Unsubscribe any time.