LiteLLM: Mehrere Schwachstellen
WID-SEC-2026-3864 · first 12.10.2026 · updated 12.10.2026 · CVSS 6,3
What it is about
LiteLLM ist ein Gateway, das eine einheitliche Schnittstelle für verschiedene Large Language Models (LLMs) bietet. Ein entfernter, authentisierter Angreifer kann mehrere Schwachstellen in LiteLLM ausnutzen, um Informationen offenzulegen, Daten zu manipulieren und Sicherheitsmaßnahmen zu umgehen.
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
- Sicherheitsmaßnahmen zu umgehen
Am I affected?
Affected according to the BSI:
- Open Source LiteLLM <=1.95.0
- Open Source LiteLLM <=1.94.0
The installed version is usually shown under “Help → About” or in the device’s admin interface.
What helps?
Update to at least:
- Open Source LiteLLM <=1.95.0
- Open Source LiteLLM <=1.94.0
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 Advisory Database vom 2026-10-11 github.com
- GitHub Advisory Database vom 2026-10-11 github.com
CVE: CVE-2026-108574, CVE-2026-108575
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.