Vulnerability · Published Jul 29, 2025 · Assigned by mitre
CVE-2025-46059
Critical 9.8
In plain English
A critical-severity code injection in the affected software. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.8% (higher than 58% of all known vulnerabilities).
Official 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.
Affected products (as reported)
Weakness: CWE-94 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H