CVE-2023-36281 langchain vulnerable to arbitrary code execution

Critical 9.8 Published 22 Aug 2023 Updated 15 Oct 2024

Remote attackers can execute arbitrary code via crafted JSON files in LangChain's load_prompt function, requiring library upgrades.

Exploited in the wild: Not known
Login needed: Not needed
Attackable: Over the internet
Victim action needed: Not needed
Fix: Available

What is CVE-2023-36281?

CVE-2023-36281 is a critical code injection vulnerability in n/a, published on 22 Aug 2023. An attacker can exploit it over the internet without logging in, with no action from the victim.

Official description

An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via a JSON file to load_prompt. This is related to __subclasses__ or a template.

Weakness: CWE-94

Which versions are affected by CVE-2023-36281?

3 open source packages ship an affected version, including langchain. It affects 1 product.

Package	Affected	Fixed in
`langchain` PyPI	All versions	`0.0.171`
`langchain` PyPI	All versions	`0.0.312`
`langchain` PyPI	All versions	`0.0.312`

Products include Langchain Langchain.

How do I fix CVE-2023-36281?

Upgrade langchain to a fixed version for your release line: 0.0.171 or 0.0.312.

Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.

Is CVE-2023-36281 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2023-36281 exists.

Public exploit code: 1 proofs of concept on GitHub.

Sources

Also known as GHSA-7gfq-f96f-g85j, PYSEC-2023-151.