CVE-2025-46059

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

9.8

Vector

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

Exploitability: 3.9 / Impact: 5.9

Source: 134c704f-9b21-4f2e-91b3-4a467353bcc0 (Secondary)

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.

Related CWEs

CWE-94

Improper Control of Generation of Code ('Code Injection')

The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.

References (4)

https://github.com/Jr61-star/CVEs/blob/main/CVE-2025-46059.md

Source: cve@mitre.org

https://github.com/langchain-ai/langchain-community/issues/217#issuecomment-3144824471

Source: cve@mitre.org

https://github.com/langchain-ai/langchain/issues/30833

Source: cve@mitre.org

https://python.langchain.com/docs/security/

Source: cve@mitre.org

Timeline

No history available yet.