LangChain: Mehrere Schwachstellen
WID-SEC-2026-3776 · first 07.10.2026 · updated 07.10.2026 · CVSS 7,1
What it is about
LangChain ist ein Open-Source-Framework, das die Entwicklung von Anwendungen mit großen Sprachmodellen (LLMs) erleichtert Ein entfernter, authentisierter Angreifer kann mehrere Schwachstellen in LangChain ausnutzen, um Informationen offenzulegen und Daten zu manipulieren.
Under what conditions?
Over the network, but only with valid access (login required), for example with stolen credentials or as an insider.
What can happen in the worst case
An attacker could use the vulnerability to
- Informationen offenzulegen
- Daten zu manipulieren
Am I affected?
Affected according to the BSI:
- Open Source LangChain <1.1.1
- Open Source LangChain <1.3.1
The installed version is usually shown under “Help → About” or in the device’s admin interface.
What helps?
Update to at least:
- Open Source LangChain 1.1.1
- Open Source LangChain 1.3.1
Is the vulnerability already being exploited?
None of the CVEs is in the CISA catalogue of exploited vulnerabilities. That does not mean there are no attacks, only that none are documented.
Information and sources
- Original BSI advisory (WID)
- GitHub Security Advisory GHSA-5x6v-p487-7qh2 vom 2026-10-06 github.com
- GitHub Security Advisory vom 2026-10-06 github.com
CVE: CVE-2026-105799, CVE-2026-106119
Source: BSI warning and information service (CERT-Bund); CISA. The assessment of the conditions is my reading of the BSI text; the external pages are in their original language.