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.
| Vendor | Product | Versions |
|---|---|---|
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 TrainingVulnerability Scanning
Discover vulnerabilities in your applications and infrastructure before attackers do.
Scan Now