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.
Published:Jul 29, 2025
Last Modified:Apr 15, 2026
EPS:Jul 29, 2025
EPSS Score:0.0024
CVSS Score:9.8
Affected Products
Vendor
Product
Action
Vendor
Langchain
Product
Langchain
Langchain
Langchain
Vendor
Langchain-ai
Product
Langchain
Langchain-ai
Langchain
Exploits
No exploit reference
Common Weakness Enumeration
Common Attack Pattern Enumeration and Classification (CAPEC)
Related CVEs
Common Vulnerability Scoring System
Attack Vector
Network
Adjacent
Local
Physical
Privileges Required
None
Low
High
User Interaction
None
Required
Scope
Unchanged
Changed
Confidentiality
None
Low
High
Integrity
None
Low
High
Availability
None
Low
High
