CVE-2025-46059

9.8 CRITICAL
Published: July 29, 2025 Modified: April 15, 2026
View on NVD

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.

AI Explanation

Get an AI-powered plain-language explanation of this vulnerability and remediation steps.

Login to generate AI explanation

CVSS v3.x Details

0.0 Low Medium High Critical 10.0
Vector String
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References to Advisories, Solutions, and Tools

Patch Vendor Advisory Exploit Third Party Advisory

4 reference(s) from NVD

Quick Stats

CVSS v3 Score
9.8 / 10.0
EPSS (Exploit Probability)
0.2%
47th percentile
Exploitation Status
Not in CISA KEV

Weaknesses (CWE)