CVE-2025-46059: Code Injection

Published Jul 29, 2025

Updated

langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the GmailToolkit component. This vulnerability allows attackers to execute arbitrary code and compromise the application via a crafted email message. NOTE: this is disputed by the Supplier because the code-execution issue was introduced by user-written code that does not adhere to the LangChain security practices.

Affected Software

1 affected component

Langchain langchain-ai

Event History

Jul 29, 2025

CVE Published

via MITRE·12:00 AM

Data Sourced

via MITRE·12:00 AM

Description

Data Sourced

via NVD·03:15 PM

DescriptionSeverityWeakness

Frequently Asked Questions

What is the severity of CVE-2025-46059?

CVE-2025-46059 is classified as a critical vulnerability due to its potential to allow arbitrary code execution.

How do I fix CVE-2025-46059?

To fix CVE-2025-46059, update to the latest version of langchain-ai that addresses this vulnerability.

What is the main impact of CVE-2025-46059?

The main impact of CVE-2025-46059 is that attackers can compromise the application by sending a crafted email message.

Which component of langchain-ai is affected by CVE-2025-46059?

CVE-2025-46059 affects the GmailToolkit component of langchain-ai.

Is CVE-2025-46059 an injection vulnerability?

Yes, CVE-2025-46059 is an indirect prompt injection vulnerability.