CVE-2025-46059

  1. OpenCVE
  2. Vulnerabilities (CVE)
  3. CVE-2025-46059
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 /10

CVSS v3 : CRITICAL

V3 Legend

Vector :

Exploitability : 3.9 / Impact : 5.9

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction NONE

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact HIGH

Scope UNCHANGED

References
Link Resource
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/
Configurations

No configuration.

History

04 Aug 2025, 00:15

Type Values Removed Values Added
References
  • () https://github.com/langchain-ai/langchain-community/issues/217#issuecomment-3144824471 -
  • () https://python.langchain.com/docs/security/ -
Summary (en) 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. (en) 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.

31 Jul 2025, 18:42

Type Values Removed Values Added
Summary
  • (es) Se descubrió que langchain-ai v0.3.51 contenía una vulnerabilidad de inyección indirecta de mensajes en el componente GmailToolkit. Esta vulnerabilidad permite a los atacantes ejecutar código arbitrario y comprometer la aplicación mediante un mensaje de correo electrónico manipulado.

29 Jul 2025, 15:15

Type Values Removed Values Added
New CVE
Information

Published : 2025-07-29 15:15

Updated : 2025-08-04 00:15

NVD link : CVE-2025-46059

Mitre link : CVE-2025-46059

CVE.ORG link : CVE-2025-46059

JSON object : View

Products Affected

No product.

CWE
CWE-94

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