BerriAI · LiteLLM · published 2026-04-06
CVE-2026-35030LiteLLM has an authentication bypass via OIDC userinfo cache key collision
Routine No exploitation evidence; EPSS 0.6%.
CVE-2026-35030 is not known to be exploited in the wild. EPSS estimates a 0.6% chance of exploitation in the next 30 days, higher than 51% of all CVEs. This LiteLLM vulnerability: CVSS 9.4 (v4.0), attacks can be automated, a successful attack gives total control of the component. Fixed upstream in LiteLLM 1.83.0. Routine: patch when convenient.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in LiteLLM 1.83.0.
Patch events
AI toolingLiteLLM
LiteLLM security release: 1.83.0
Upgrade to
1.83.0Why: CVE-2026-35029: EPSS 39% chance of exploitation in 30 days, with critical impact.
Exploit intelligence#
| Signal | Value | Source |
|---|---|---|
| Known exploited | No | CISA KEV |
| Ransomware use | — | CISA KEV |
| EPSS (30-day exploitation probability) | 0.6% (51th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 9.4 (v4.0)CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:N/SC:H/SI:H/SA:N | CNA / CISA ADP |
| SSVC exploitation | none | CISA Vulnrichment |
| SSVC automatable | Yes | CISA Vulnrichment |
| SSVC technical impact | total | CISA Vulnrichment |
Affected versions (from the CVE record)#
- BerriAI litellm
< 1.83.0(affected)
Description (from the CVE record)#
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.0, when JWT authentication is enabled (enable_jwt_auth: true), the OIDC userinfo cache uses token[:20] as the cache key. JWT headers produced by the same signing algorithm generate identical first 20 characters. This configuration option is not enabled by default. Most instances are not affected. An unauthenticated attacker can craft a token whose first 20 characters match a legitimate user's cached token. On cache hit, the attacker inherits the legitimate user's identity and permissions. This affects deployments with JWT/OIDC authentication enabled. Fixed in v1.83.0.
Quoted from the CVE Program record.