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.

INFO

Published Date :

2025-07-29T00:00:00.000Z

Last Modified :

2025-08-03T23:20:43.149Z

Source :

mitre
AFFECTED PRODUCTS

The following products are affected by CVE-2025-46059 vulnerability.

Vendors Products
Langchain
  • Langchain
Langchain-ai
  • Langchain
REFERENCES

Here, you will find a curated list of external links that provide in-depth information to CVE-2025-46059.

URL Resource
https://github.com/Jr61-star/CVEs/blob/main/CVE-2025-46059.md cve-icon cve-icon cve-icon
https://github.com/langchain-ai/langchain-community/issues/217#issuecomment-3144824471 cve-icon cve-icon
https://github.com/langchain-ai/langchain/issues/30833 cve-icon cve-icon cve-icon
https://nvd.nist.gov/vuln/detail/CVE-2025-46059 cve-icon
https://python.langchain.com/docs/security/ cve-icon cve-icon
https://www.cve.org/CVERecord?id=CVE-2025-46059 cve-icon
Login to claim this CVE

CVSS Vulnerability Scoring System

Detailed values of each vector for above chart.
Attack Vector
Attack Complexity
Privileges Required
User Interaction
Scope
Confidentiality Impact
Integrity Impact
Availability Impact