LangChain Experimental vulnerable to arbitrary code execution

langchain-experimental (pip)

langchain_experimental (aka LangChain Experimental) before 0.0.52, part of LangChain before 0.1.8, allows an attacker to bypass the CVE-2023-44467 fix and execute arbitrary code via the import, subclasses, builtins, globals, getattribute, bases, mro, or base attribute in Python code. These are not prohibited by pal_chain/base.py.

Fix it

pip install --upgrade "langchain-experimental>=0.0.52"

First seen: 26 Feb 2024
Last update: 26 Feb 2024, 18:30 UTC
Fixed in: langchain-experimental 0.0.52
Identifiers: CVE-2024-27444
Source: GitHub advisory
On the menu as: PyPI packages
LLM gateways

Check this repository for exposure to one security incident from pwned.coffee. Report first, change nothing until I say so.

## LangChain Experimental vulnerable to arbitrary code execution
Severity: critical. Patch status: patched.
Affected: langchain-experimental (pip)
Fixed in: langchain-experimental 0.0.52
Ids: CVE-2024-27444

langchain_experimental (aka LangChain Experimental) before 0.0.52, part of LangChain before 0.1.8, allows an attacker to bypass the CVE-2023-44467 fix and execute arbitrary code via the import, subclasses, builtins, globals, getattribute, bases, mro, or base attribute in Python code. These are not prohibited by pal_chain/base.py.

## Steps
1. This incident involves a provider (ai-gateways). Search config, CI and env templates (.env.example, wrangler.toml, vercel.json, terraform, workflow secrets) for credentials stored there. List each secret by name, where it is used, and how to rotate it. Never print secret values.

## Report
A table: file, product or package, version in use, affected yes/no, exact fix. Then anything a human has to check outside the repo.

If you have the pwned.coffee MCP server (https://pwned.coffee/mcp), call lookup_cve("CVE-2024-27444") for the latest, and check_repo with this repo's lockfiles, Dockerfiles and workflows for a full receipt.
Sources: https://github.com/advisories/GHSA-v8vj-cv27-hjv8 https://github.com/langchain-ai/langchain/commit/de9a6cdf163ed00adaf2e559203ed0a9ca2f1de7 https://github.com/pypa/advisory-database/tree/main/vulns/langchain-experimental/PYSEC-2026-375.yaml https://nvd.nist.gov/vuln/detail/CVE-2024-27444 https://pypi.org/project/langchain-experimental
https://pwned.coffee/i/langchain-experimental-vulnerable-to-arbitrary-code-exec-cve-2024-27444

Sources

Wrong fix version, or a source we missed? Send it back to chef@pwned.coffee with the source, and we'll correct it here.

Totalone very hot coffee