CVE-2025-46059

9.8 criticalEPSS 0.8%

Critical (9.8). EPSS 0.8% chance of exploitation in the next 30 days.

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.

Severity

CVSS 3.1

9.8 critical

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

EPSS: 0.8% chance of exploitation in the next 30 days; higher than 57% of CVEs (scores of 2026-10-31)
CWE: CWE-94
Published: 2025-07-29
Modified: 2026-06-17
Record from: the NVD, synced 2026-10-19

References

https://github.com/Jr61-star/CVEs/blob/main/CVE-2025-46059.md
https://github.com/langchain-ai/langchain-community/issues/217#issuecomment-3144824471
https://github.com/langchain-ai/langchain/issues/30833
https://python.langchain.com/docs/security/

Check your stack JSON