CVE-2026-42208 — LiteLLM — Corretto in 1.83.7
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before version 1.83.7, a database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route (for example POST /chat/completions) and reach this query through the proxy's error-handling path. An attacker could read data from the proxy's database and may be able to modify it, leading to unauthorised access to the proxy and the credentials it manages. This issue has been patched in version 1.83.7.
Versioni corrette
Scegli la versione relativa al prodotto e al ramo installato.
| Prodotto | Versioni corrette |
|---|---|
| LiteLLM | 1.83.7 |
Sfruttata attivamente
- Nel catalogo CISA delle vulnerabilità sfruttate dal 8 mag 2026
- Le agenzie federali statunitensi devono correggerla entro il 11 mag 2026 (direttiva BOD 22-01)
- Attaccata 11 giorni prima che la vulnerabilità fosse resa pubblica
Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.
Fonte: CISA KEV · 27 ago 2026 23 lug 2026 8 mag 2026 27 apr 2026
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:HProdotti coinvolti
| Vendor | Prodotto | Versioni |
|---|---|---|
| litellm | litellm | < 1.83.7 |
Articoli correlati
This product uses the NVD API but is not endorsed or certified by the NVD.