VULNERABILITY INTELLIGENCE
CVE-2025-46059
CVSS score9.8 CRITICAL
EPSS probability0.84%
CISA KEVNot currently listed
Published2025-07-29
Last modified2026-06-17
CVSS vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
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.
Weakness classification
- 134c704f-9b21-4f2e-91b3-4a467353bcc0: CWE-94