CVE-2025-46059

Published Jul 29, 2025

Last updated 9 days ago

Overview

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.
Source
cve@mitre.org
NVD status
Deferred
CNA Tags
disputed

Risk scores

CVSS 3.1

Type
Secondary
Base score
9.8
Impact score
5.9
Exploitability score
3.9
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Severity
CRITICAL

Weaknesses

134c704f-9b21-4f2e-91b3-4a467353bcc0
CWE-94

Social media

Hype score
Not currently trending