RCE in N/a

CVE-2025-46059

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.

Vulnerability class: RCE (Remote Code Execution)

Published · last modified .

CVSS v3 metric

CVSS v3 base score 9.8 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.

EPSS exploit prediction

EPSS: 0.007 (52.6th percentile), scored .

Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 53rd percentile — 52.6% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.

EPSS trend (30 days)EPSS over the last 30 days for CVE-2025-46059: held from 0.007 to 0.007.

EPSS over last 30 days · oldest: 0.007 · newest: 0.007 · change: +0.000

Weakness classification (CWE)

References

Frequently asked questions

What is CVE-2025-46059?
CVE-2025-46059 is a critical-severity vulnerability in N/a, classified under Code Injection. CVSS score: 9.8/10. Published 2025-07-29.
How severe is CVE-2025-46059?
Critical severity. CVSS v3 base score is 9.8 out of 10.