CVE-2025-46059
Last modified
CVE-2025-46059 is a critical-severity vulnerability rated 9.8/10 on the CVSS scale. 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. EPSS estimates a 0.67% chance of exploitation in the next 30 days.
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.
Metrics
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weakness Enumeration
References
Timeline
- Published
- Last Modified
- Status
- Deferred
Frequently Asked Questions
What is CVE-2025-46059?
How severe is CVE-2025-46059?
How do I fix CVE-2025-46059?
Are you affected by CVE-2025-46059?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
