SQL Injection in langchain-ai/langchain
langchain-ai/langchain
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| langchain-community PyPI |
|
|
| langchain PyPI |
|
|
langchain-ai/langchain
| Product | Affected | Fixed in |
|---|---|---|
| langchain-community PyPI |
|
|
| langchain PyPI |
|
|
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.
From the CVE record · @huntr_ai
GraphCypherQAChain in langchain-ai/langchain version 0.2.5 is vulnerable to injection through a malicious prompt. An attacker who can supply such a prompt may manipulate or extract data, delete data, or access data across tenants. The input does not specify network access or authentication requirements.
Engineers running PyPI langchain-community versions >=0.2.0 <0.3.0 or PyPI langchain versions <0.2.0 should check their deployments.