CVE-2024-7042

published 29 Oct 2024 · updated 15 Oct 2025

Prompt Injection in langchain-ai/langchainjs Leading to SQL Injection

4.9MediumCVSS 4.9EPSS 0%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 0%. Fixed in 0.3.1.

A vulnerability in the GraphCypherQAChain class of langchain-ai/langchainjs versions 0.2.5 and all versions with this class allows for prompt injection, leading to SQL injection. This vulnerability permits unauthorized data manipulation, data exfiltration, denial of service (DoS) by deleting all data, breaches in multi-tenant security environments, and data integrity issues. Attackers can create, update, or delete nodes and relationships without proper authorization, extract sensitive data, disrupt services, access data across different tenants, and compromise the integrity of the database.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
langchain-ai<0.3.10.3.1

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2024-7042 severity on Zeptric[![CVE-2024-7042](https://zeptric.io/badge/cve/CVE-2024-7042.svg)](https://zeptric.io/cve/CVE-2024-7042)