---
title: "CVE-2023-44467: langchain_experimental vulnerable to arbitrary code execution via PALChain in the python exec method"
url: https://erroneo.us/security/cve/CVE-2023-44467/
description: "CVE-2023-44467 (langchain-experimental (PyPI)): langchainexperimental (aka LangChain Experimental) in LangChain before 0.0.306 allows an attacker to bypass…"
type: vulnerability-record
section: "Security Digest"
date_published: 2023-10-09
date_modified: 2026-10-21
publisher: erroneo.us
author: erroneo.us Security Desk
cve: "CVE-2023-44467"
kev: false
cvss: 9.8
epss: 0.01039
license: All rights reserved. Quote with attribution and a link.
---

# CVE-2023-44467: langchain_experimental vulnerable to arbitrary code execution via PALChain in the python exec method

**Signal:** Critical and remotely reachable. No known exploitation yet, but it is network-reachable without credentials. (Computed from CISA KEV, EPSS and CVSS; not an editorial verdict.)

## Should you act?

- No confirmed exploitation. It is not in CISA’s KEV catalog. That can change quickly after a public write-up; re-check if you are affected.
- EPSS 1.0% , percentile 64: FIRST’s model estimates a 1.0% chance of exploitation activity in the next 30 days, higher than 64% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes langchain-experimental (PyPI) <= 0.0.14, no fixed version listed . Check your lockfile, including transitive dependencies.
- Editorial verdict: Check exposure. LangChain PALChain: Prompt Injection to RCE (CVE-2023-44467) — Only apps that feed untrusted text into PALChain (or similar LLM-to-Python chains) are at risk, but for them it is full code execution, and blocklist fixes kept getting bypassed, so remove the pattern rather than trust the patch.

## What it is

langchainexperimental (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 palchain/base.py.

## Affected packages

- PyPI `langchain-experimental` <= 0.0.14 → fixed: none listed

## Affected products (CVE record)

- n/a n/a: see advisory

## Severity

- GitHub CVSS 3.1: 9.8 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H`

## Exploitation

- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- FIRST EPSS (model of 2026-10-21): 1.04% probability of exploitation activity in the next 30 days; percentile 64.

## Sources

- [GitHub Advisory GHSA-gjjr-63x4-v8cq](https://github.com/advisories/GHSA-gjjr-63x4-v8cq)
- [CVE.org record CVE-2023-44467](https://www.cve.org/CVERecord?id=CVE-2023-44467)
- [NVD entry CVE-2023-44467](https://nvd.nist.gov/vuln/detail/CVE-2023-44467)
- [github.com](https://github.com/langchain-ai/langchain/commit/4c97a10bd0d9385cfee234a63b5bd826a295e483)
- [github.com](https://github.com/langchain-ai/langchain/pull/11233)
- [github.com](https://github.com/pypa/advisory-database/tree/main/vulns/langchain-experimental/PYSEC-2023-194.yaml)
- [pypi.org](https://pypi.org/project/langchain-experimental/0.0.14)

---
Source page: https://erroneo.us/security/cve/CVE-2023-44467/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt
