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)

EPSS: 0.007 (49.5th percentile) — read the EPSS interpretation.

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.

Affected products

  • N/a — versions n/a

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.