CVE-2023-44467

Affects: LangChain

CVSS: CRITICAL · 9.8v3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Published: 2023-10-09
Source: nvd.nist.gov/vuln/detail/CVE-2023-44467

Description

langchain_experimental (aka LangChain Experimental) in LangChain before 0.0.306 allows an attacker to bypass the CVE-2023-36258 fix and execute arbitrary code via import in Python code, which is not prohibited by pal_chain/base.py.

References

https://github.com/langchain-ai/langchain/commit/4c97a10bd0d9385cfee234a63b5bd826a295e483
https://github.com/langchain-ai/langchain/commit/4c97a10bd0d9385cfee234a63b5bd826a295e483

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2023-44467 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course →·Browse MITRE ATLAS techniques

Related AI/LLM CVEs

CVE-2026-45134(HIGH)
CVE-2026-44843(HIGH)
CVE-2026-45401(HIGH)
CVE-2026-7844(MEDIUM)
CVE-2026-41481(MEDIUM)
CVE-2026-30617(HIGH)
CVE-2026-40087(MEDIUM)
CVE-2026-34070(HIGH)

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming