CVE-2024-7042

Name of the Vulnerable Software and Affected Versions langchain-ai/langchainjs versions 0.2.5 and later

Description The issue allows for prompt injection, leading to SQL injection, which can result in 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.

Recommendations For langchain-ai/langchainjs version 0.2.5, consider disabling the GraphCypherQAChain class until a patch is available to prevent prompt injection and subsequent SQL injection attacks. At the moment, there is no information about a newer version that contains a fix for this vulnerability.