Indirect Prompt Injection Vulnerability in langchain-ai GmailToolkit
CVE-2025-46059

9.8CRITICAL

Key Information:

Vendor

langchain-ai

Status
GmailToolkit
Vendor
CVE Published:
29 July 2025

What is CVE-2025-46059?

The langchain-ai GmailToolkit component has been found to possess an indirect prompt injection vulnerability in version 0.3.51. Attackers can exploit this flaw to execute arbitrary code by sending specially crafted email messages, potentially compromising the integrity and security of the application. This vulnerability underscores the importance of stringent email handling and validation mechanisms within applications to mitigate such risks.

References

https://github.com/langchain-ai/langchain/issues/30833
https://github.com/Jr61-star/CVEs/blob/main/CVE-2025-4605...

CVSS V3.1

Score:
9.8
Severity:
CRITICAL
Confidentiality:
High
Integrity:
High
Availability:
High
Attack Vector:
Network
Attack Complexity:
Low
Privileges Required:
None
User Interaction:
None
Scope:
Unchanged

Timeline

  • Vulnerability published

  • Vulnerability Reserved

.
CVE-2025-46059 : Indirect Prompt Injection Vulnerability in langchain-ai GmailToolkit