Critical severity9.8NVD Advisory· Published Jul 29, 2025· Updated Apr 15, 2026

CVE-2025-46059

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.

AI Insight

LLM-synthesized narrative grounded in this CVE's description and references.

Affected products

Langchain AI/Langchainreferences

Patches

Vulnerability mechanics

References

github.com/Jr61-star/CVEs/blob/main/CVE-2025-46059.mdnvd
github.com/langchain-ai/langchain-community/issues/217nvd
github.com/langchain-ai/langchain/issues/30833nvd
python.langchain.com/docs/security/nvd

News mentions

No linked articles in our index yet.

cvss	0.637
epss	0.001
exploit	0.000
kev	0.000
patch	0.000
ransomware	0.000