CVE-2025-46059 | THREATINT

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.

PUBLISHED Reserved 2025-04-22 | Published 2025-07-29 | Updated 2025-08-03 | Assigner mitre

References

github.com/langchain-ai/langchain/issues/30833

github.com/Jr61-star/CVEs/blob/main/CVE-2025-46059.md

github.com/langchain-ai/langchain-community/issues/217

python.langchain.com/docs/security/

cve.org (CVE-2025-46059)

nvd.nist.gov (CVE-2025-46059)

Download JSON