همهٔ گزارش‌ها
زیاد

langchain-core: Langchain indirect propmpt injection

متن اصلی

نسخه‌های متأثر

نسخه‌های متأثر
نامشخص
نسخهٔ اصلاح‌شده
اعلام نشده

بهره‌برداری

CVE-2025-46059

احتمال بهره‌برداری در ۳۰ روز آینده: 0.84%

FIRST EPSS · ۱۴۰۵/۰۸/۲۸

شرح آسیب‌پذیری

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.

A prompt injection vulnerability was found in the Langchain AI project. Users who leverage the GmailToolkit component are at risk of an attacker creating a malicious email. This vulnerability could allow code execution in the context of the running Python application.