Описание
LangGraph's SQLite store implementation has a SQL Injection Vulnerability
A SQL injection vulnerability exists in the langchain-ai/langgraph repository, specifically in the LangGraph's SQLite store implementation. The affected version is langgraph-checkpoint-sqlite 2.0.10. The vulnerability arises from improper handling of filter operators ($eq, $ne, $gt, $lt, $gte, $lte) where direct string concatenation is used without proper parameterization. This allows attackers to inject arbitrary SQL, leading to unauthorized access to all documents, data exfiltration of sensitive fields such as passwords and API keys, and a complete bypass of application-level security filters.
Ссылки
- https://nvd.nist.gov/vuln/detail/CVE-2025-8709
- https://github.com/langchain-ai/langgraph/pull/5666
- https://github.com/langchain-ai/langgraph/commit/bc9d45b476101e441cb1cc602dea03eb29232de4
- https://github.com/langchain-ai/langgraph/releases/tag/checkpointsqlite%3D%3D2.0.11
- https://huntr.com/bounties/9793f4b3-76f8-44a4-989f-49a2177ee118
Пакеты
langgraph-checkpoint-sqlite
<= 2.0.10
2.0.11
Связанные уязвимости
A SQL injection vulnerability exists in the langchain-ai/langchain repository, specifically in the LangGraph's SQLite store implementation. The affected version is langgraph-checkpoint-sqlite 2.0.10. The vulnerability arises from improper handling of filter operators ($eq, $ne, $gt, $lt, $gte, $lte) where direct string concatenation is used without proper parameterization. This allows attackers to inject arbitrary SQL, leading to unauthorized access to all documents, data exfiltration of sensitive fields such as passwords and API keys, and a complete bypass of application-level security filters.
A SQL injection vulnerability exists in the langchain-ai/langchain repository, specifically in the LangGraph's SQLite store implementation. The affected version is langgraph-checkpoint-sqlite 2.0.10. The vulnerability arises from improper handling of filter operators ($eq, $ne, $gt, $lt, $gte, $lte) where direct string concatenation is used without proper parameterization. This allows attackers to inject arbitrary SQL, leading to unauthorized access to all documents, data exfiltration of sensitive fields such as passwords and API keys, and a complete bypass of application-level security filters.
Уязвимость фреймворка для создания приложений на основе комбинирования языковах моделей (LLM) LangChain, связанная с непринятием мер по защите структуры SQL-запроса, позволяющая нарушителю получить несанкционированный доступ к защищаемой информации