LLMHigh
CVE-2024-8309: A vulnerability in the GraphCypherQAChain class of langchain-ai/langchain version 0.2.5 allows for S…
- Occurred
- Oct 29, 2024
- Published
- Oct 29, 2024
- Source
- NVD CVE
Summary
A vulnerability in the GraphCypherQAChain class of langchain-ai/langchain version 0.2.5 allows for SQL injection through prompt injection. This vulnerability can lead to 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.
Tags
- CVE
- CVE-2024-8309
- cvss:CRITICAL
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: Vulnerability in LangChain LLM framework allows SQL injection via prompt injection, enabling data exfiltration and DoS.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8