CVE-2025-46059

langchain-core: Langchain indirect propmpt injection

Published Jul 29, 2025 CVSS 3.1 · 9.8 Critical EPSS < 1% KEV · Not listed
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.

Remediation

No solution or workaround provided in the CVE record

Tracking

Sign in to view the affected projects.

Advisories

Source ID Title
EUVD EUVD EUVD-2025-23002 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.
History
Type Values Removed Values Added
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. 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.
References
Type Values Removed Values Added
First Time appeared Langchain
Langchain langchain
Langchain-ai
Langchain-ai langchain
Vendors & Products Langchain
Langchain langchain
Langchain-ai
Langchain-ai langchain
Type Values Removed Values Added
Title langchain-core: Langchain indirect propmpt injection
References
Metrics threat_severity

None

threat_severity

Important

Type Values Removed Values Added
Weaknesses CWE-94
Metrics cvssV3_1

{'score': 9.8, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H'}

ssvc

{'options': {'Automatable': 'yes', 'Exploitation': 'poc', 'Technical Impact': 'total'}, 'version': '2.0.3'}

Type Values Removed Values Added
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.
References
Weaknesses

Sources

Status
PUBLISHED
Assigner
mitre
Published
Updated
Aug 3, 2025, 11:20 PM
Reserved
Apr 22, 2025, 12:00 AM
Status
Deferred
Published
Jul 29, 2025, 3:15 PM
Modified
Jun 17, 2026, 9:25 AM
Severity
Important
Public date
Jul 29, 2025, 12:00 AM