AI Sec Watch: A Security Intelligence Platform for AI Systems

Luu, T.J.

CriticalVulnerability

CVE-2023-39659: langchain arbitrary code execution through PythonAstREPLTool._run

Source: NVD(opens in a new tab)
Identifier: CVE-2023-39659
Published: August 15, 2023
Record updated: October 9, 2026

View JSON

Affected: langchain < 0.0.325
Fixed in: 0.0.325
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 1.5%

Summary

CVE-2023-39659 affects langchain (langchain-ai) v.0.0.232 and earlier. A remote attacker can execute arbitrary code by sending a crafted script to the PythonAstREPLTool._run component. The source classifies the weakness as CWE-74, Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection').

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 9.8(critical)
Patch available: Yes
EPSS: 1.5%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on October 9, 2026.

Weaknesses and techniques

Weakness (CWE): CWE-74

Affected

Packages: langchain@< 0.0.325 (fixed: 0.0.325)
Vendors: LangChain

Classification

Attack type: Other
Attack sophistication: Trivial
AI component targeted: Framework
Impact: Confidentiality,
Integrity,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2023-39659

First tracked: February 15, 2026 at 08:35 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

Summary

Mitigation

Related items