CVE-2025-46059: langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the GmailToolkit component. This vulnerability allows att...

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.

Metrics

CVSS 3.1

9.8/10

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

EPSS Probability

0.67%

47.4th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

CWE-94

References

Timeline

Published: Jul 29, 2025
Last Modified: Jun 17, 2026
Status: Deferred

Frequently Asked Questions

What is CVE-2025-46059?

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.

How severe is CVE-2025-46059?

CVE-2025-46059 has a CVSS score of 9.8/10 (CRITICAL severity). The EPSS model estimates a 0.67% probability of exploitation in the next 30 days.

How do I fix CVE-2025-46059?

Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

How Strix Helps

Related CVEs from 2025

View all 2025CVEs →