← Back to CVEs

CVE-2025-46059

CRITICAL

9.8

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.

CVE Details

CVSS v3.1 Score9.8

SeverityCRITICAL

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

Attack VectorNETWORK

ComplexityLOW

Privileges RequiredNONE

User InteractionNONE

Published7/29/2025

Last Modified8/4/2025

Sourcenvd

Honeypot Sightings0

Weaknesses (CWE)

CWE-94

References

https://github.com/Jr61-star/CVEs/blob/main/CVE-2025-46059.md(cve@mitre.org)

https://github.com/langchain-ai/langchain-community/issues/217#issuecomment-3144824471(cve@mitre.org)

https://github.com/langchain-ai/langchain/issues/30833(cve@mitre.org)

https://python.langchain.com/docs/security/(cve@mitre.org)

IOC Correlations

No correlations recorded

This product uses data from the NVD API but is not endorsed or certified by the NVD.