Summary
Ein entfernter, authentisierter Angreifer kann mehrere Schwachstellen in LangChain ausnutzen, um Informationen offenzulegen und Daten zu manipulieren.
Product
LangChain ist ein Open-Source-Framework, das die Entwicklung von Anwendungen mit großen Sprachmodellen (LLMs) erleichtert
Vulnerabilities 2
-
Medium 6.0
LangChain: MongoDBChatMessageHistory query injection can allow cross-session access
LangChain is a framework for building LLM-powered applications. Prior to 1.3.1, MongoDBChatMessageHistory does not enforce the documented string type for an untrusted structured session identifier at runtime, allowing the identifier to be interpreted as a Mon…
-
Low 2.3
LangChain: RediSearch Filter Injection via Unescaped Tag/Text Values
LangChain is a framework for building LLM-powered applications. Prior to 1.1.1, @langchain/redis does not escape attacker-controlled values in structured RediSearch TAG filters and structured RediSearch TEXT filters, allowing injected RediSearch syntax to alt…
Revision history
-
#1
Initiale Fassung
References
-
GitHub Security Advisory GHSA-5x6v-p487-7qh2 vom 2026-10-06
https://github.com/advisories/GHSA-5x6v-p487-7qh2
-
GitHub Security Advisory vom 2026-10-06
https://github.com/langchain-ai/langchainjs/security/advisories/GHSA-m6rx-h84q-8r95