CVE Database
/

CVE-2025-46059

Back to search

CVE-2025-46059

Published: Jul 29, 2025

Modified: Aug 3, 2025

PUBLISHED

Description

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.

VendorProductVersions

n/a

n/a

affected
n/a

Security Training

Train your team to recognize and prevent security threats with our comprehensive security awareness program.

Start Training

Vulnerability Scanning

Discover vulnerabilities in your applications and infrastructure before attackers do.

Scan Now