CVE-2025-46059

critical · 9.8

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.

9.8

CVSS

0.7%

EPSS (exploit prob.)

52nd

EPSS percentile

2025-07-29

Published

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

Weaknesses

CWE-94

References

https://github.com/Jr61-star/CVEs/blob/main/CVE-2025-46059.md
https://github.com/langchain-ai/langchain-community/issues/217#issuecomment-3144824471
https://github.com/langchain-ai/langchain/issues/30833
https://python.langchain.com/docs/security/

Query this programmatically:

curl https://evil-db.io/api/v1/cve/CVE-2025-46059