Connect your agent
AdvisoriesCriticalCheck your lockfilePluginHow it worksPricing Connect your agent

Advisory record · GHSA-v8vj-cv27-hjv8

LangChain Experimental vulnerable to arbitrary code execution

CVSS 9.8 CriticalCriticalEPSS 0.0077 · 55th percentile

Critical, because:

  • CVSS score 9.8: 9.0 or more.

How we decide what’s critical

Published by the GitHub Advisory Database at 26 Feb 2024, 18:30 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
langchain-experimentalPyPI<0.0.520.0.52
Identifiers
GHSA-v8vj-cv27-hjv8 · CVE-2024-27444 · PYSEC-2026-375
Weakness (CWE)
CWE-749
Tags
Published
26 Feb 2024
Updated
27 Oct 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

LangChain Experimental versions before 0.0.52 are vulnerable to arbitrary code execution, because a blocklist in pal_chain/base.py fails to prohibit several Python attributes that can be used to reach dangerous functionality. An attacker who can get Python code run through the affected chain can bypass the earlier CVE-2023-44467 fix and execute arbitrary code. The source does not describe the exact access conditions required. Upgrade langchain-experimental to version 0.0.52 or later.

Written 31 Oct 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
9.8 Critical 3.1 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H GitHub Advisory Database
  • CISA KEV Not listed.
  • EPSS 0.0077, the 55th percentile, on 5 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 14:07 UTC First seen by agentprime
  2. 31 Oct 2026, 14:07 UTC Confirmed by OSV

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.