Vulnerabilities · 2024 · Langchain
CVE-2024-27444
Langchain-experimental vulnerability
langchain_experimental (aka LangChain Experimental) in 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.
High priority: this vulnerability is rated critical and can be attacked over the network without a login.
Affected products
Langchain-experimental. The exact versions are in the references.
What to do now
- Check your exposureFind out whether Langchain-experimental runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Limit access until thenIf you cannot update at once, take the system off the internet or restrict who can reach it.
References
- github.com/langchain-ai/langchain/commit/de9a6cdf163ed00adaf2e559203ed0a9ca2f1de7 · Patch
- nvd.nist.gov/vuln/detail/CVE-2024-27444
- github.com/advisories/GHSA-v8vj-cv27-hjv8
- github.com/pypa/advisory-database/tree/main/vulns/langchain-experimental/PYSEC-2026-375.ya
- pypi.org/project/langchain-experimental
- nvd.nist.gov/vuln/detail/CVE-2024-27444
- cve.org/CVERecord?id=CVE-2024-27444
More vulnerabilities in Langchain products
CVE-2025-68665CVE-2025-68664CVE-2025-2828CVE-2024-58340CVE-2024-46946CVE-2024-38459CVE-2024-28088CVE-2024-21513All 34
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.