CVE-2025-46059
28Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 9.8epss 0.7%
exploitation probability
0.7%top 49% of all CVEs
observed exploitation
nono source reports it
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.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Affected products
n/a · n/a