LangChain (openai, text-splitters): Mehrere Schwachstellen ermöglichen Offenlegung von Informationen und SSRF-Umgehung
WID-SEC-2026-1275 · first 27.04.2026 · updated 29.06.2026 · CVSS 6,5
What it is about
LangChain ist ein Open-Source-Framework, das die Entwicklung von Anwendungen mit großen Sprachmodellen (LLMs) erleichtert Ein entfernter, anonymer Angreifer kann mehrere Schwachstellen in LangChain ausnutzen, um SSRF-Schutzmaßnahmen zu umgehen und Informationen offenzulegen.
Under what conditions?
Over the network and without logging in. This is the most dangerous combination: attackers can scan reachable devices automatically.
What can happen in the worst case
An attacker could use the vulnerability to
- SSRF-Schutzmaßnahmen zu umgehen
- Informationen offenzulegen
Am I affected?
Affected according to the BSI:
- Open Source LangChain text-splitters <1.1.2
- Open Source LangChain openai <1.1.14
- IBM Business Automation Workflow
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 text-splitters 1.1.2
- Open Source LangChain openai 1.1.14
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)
- LangChain GitHub vom 2026-04-26 github.com
- LangChain GitHub vom 2026-04-26 github.com
- EU Vulnerability Database vom 2026-04-26 euvd.enisa.europa.eu
- EU Vulnerability Database vom 2026-04-26 euvd.enisa.europa.eu
- IBM Security Bulletin 7278339 vom 2026-06-29 www.ibm.com
CVE: CVE-2026-41481, CVE-2026-41488
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.