CVE-2025-46059 - CVE House
Back to Database
Status published Unknown CVE-2025-46059

langchain-ai v0.3.51 was discovered to contain an indirect prompt injection...

Vulnerability 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.

Impact Analysis

Refer to official advisory for detailed impact metrics.

Remediation

Ensure systems are updated to the latest vendor-supplied patch levels.

THREAT MONITOR

Am I Vulnerable?

Launch our assessment wizard to check if your infrastructure is exposed to • CVE-2025-46059

Credits & Attribution

No credits recorded in the NVD database.

References

More from n/a

View All →
CVE-2025-9910
Versions of the package jsondiffpatch before 0.7.2 are vulnerable to...
Low 2.3
CVE-2025-9802
RemoteClinic profile.php sql injection
Medium 5.1
CVE-2025-9799
Langfuse Webhook promptRouter.ts promptChangeEventSourcing server-side request forgery
Low 2.3
CVE-2025-9775
RemoteClinic edit-my-profile.php unrestricted upload
Medium 6.9
CVE-2025-9774
RemoteClinic edit-patient.php information disclosure
Medium 5.3

Affected Vendor

Affected Software

Unknown
Vulnerable Versions:
Unknown

Timeline

Official Publish: July 29th, 2025
Last Modified: August 3rd, 2025
Added to House: July 22nd, 2026

CVSS Vectors

No vector data available

Weaknesses (CWE)

No CWE data available

MITRE ATT&CK TTPs

No associated TTPs found for this vulnerability.