LangChain: Schwachstelle ermöglicht Offenlegung von Informationen und Umgehen von Sicherheitsvorkehrungen
WID-SEC-2026-1958 · first 17.06.2026 · updated 07.10.2026 · CVSS 5,1
What it is about
LangChain ist ein Open-Source-Framework, das die Entwicklung von Anwendungen mit großen Sprachmodellen (LLMs) erleichtert Ein lokaler Angreifer kann eine Schwachstelle in LangChain ausnutzen, um Informationen offenzulegen, und um Sicherheitsvorkehrungen zu umgehen.
Under what conditions?
Only with access to the device or an account on it. Often the second step after a phishing email.
What can happen in the worst case
An attacker could use the vulnerability to
- Informationen offenzulegen
- Sicherheitsvorkehrungen zu umgehen
Am I affected?
Affected according to the BSI:
- Open Source LangChain <1.3.9
- Open Source LangChain Anthropic <1.4.6
- SUSE openSUSE
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 1.3.9
- Open Source LangChain Anthropic 1.4.6
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-gr75-jv2w-4656 vom 2026-06-16 github.com
- openSUSE Security Update OPENSUSE-SU-2026:11946-1 vom 2026-10-06 lists.opensuse.org
CVE: CVE-2026-55443
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.