criticalCVSS 9.8NVD status: Deferred

CVE-2025-46059

langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the GmailToolkit component.

ComponentLangChain
Severitycritical (CVSS 9.8)
CVSS vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Published (NVD)2025-07-29
Last modified2026-06-17
Affected versionsnot published yet, see the advisory
Fixed insee the vendor advisory
WeaknessCWE-94
CISA KEVnot listed

NVD 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.

Does CVE-2025-46059 hit the version you run?Paste your docker-compose.yml, requirements.txt or package.json. The scanner checks your pinned versions against this CVE and every other one we track for LangChain.
Check my stack

What to do

  • NVD lists no fixed version yet: follow the vendor advisory below and keep LangChain off the public internet until a fix ships.
  • Do not expose the component's API or UI to the internet without authentication in front of it.

Sources

Other LangChain CVEs

All LangChain CVEs