CVE-2026-35030
CVE-2026-35030 is a critical-severity vulnerability in Litellm with a CVSS 3.x base score of 9.1. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-287.
Key facts
- Severity: Critical (CVSS 3.x base score 9.1)
- CVSS v4: 9.4
- EPSS exploit prediction: 0% (39th percentile)
- Actively exploited: Not listed in CISA KEV
- EU (EUVD) id: EUVD-2026-19372
- Weakness: CWE-287
- Affected product: Litellm
- Published:
- Last modified:
Description
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.
Frequently asked questions
- What is CVE-2026-35030?
- 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.
- How severe is CVE-2026-35030?
- CVE-2026-35030 has a CVSS 3.x base score of 9.1, rated critical severity. It is exploitable over network with low attack complexity, requires no privileges and no user interaction. Impact on confidentiality is high, integrity high, and availability none.
- Is CVE-2026-35030 being actively exploited?
- It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (39th percentile), an estimate of the probability of exploitation in the next 30 days.
- What products are affected by CVE-2026-35030?
- CVE-2026-35030 affects Litellm. See the affected-products list for the exact vulnerable versions.
- How do I fix CVE-2026-35030?
- Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its critical severity, prioritise patching exposed systems.
- Does CVE-2026-35030 have an EU (EUVD) identifier?
- Yes. CVE-2026-35030 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-19372.
- When was CVE-2026-35030 published?
- CVE-2026-35030 was published on 2026-04-06 and last updated on 2026-06-30.
References
- https://github.com/BerriAI/litellm/security/advisories/GHSA-jjhc-v7c2-5hh6
- https://access.redhat.com/errata/RHSA-2026:13545
- https://access.redhat.com/errata/RHSA-2026:28960
- https://access.redhat.com/errata/RHSA-2026:30056
- https://access.redhat.com/security/cve/CVE-2026-35030
- https://bugzilla.redhat.com/show_bug.cgi?id=2455509
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-35030.json
Affected products (1)
- cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*
More vulnerabilities in Litellm
- CVE-2026-49468 — Critical (CVSS 9.8): LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, This…
- CVE-2026-42208 — Critical (CVSS 9.8): LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before…
- CVE-2024-5751 — Critical (CVSS 9.8): BerriAI/litellm version v1.35.8 contains a vulnerability where an attacker can achieve remote code execution. The…
- CVE-2024-2952 — Critical (CVSS 9.8): BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The…
- CVE-2026-47102 — High (CVSS 8.8): LiteLLM prior to 1.83.10 allows a user to modify their own user_role via the /user/update endpoint. While the endpoint…
- CVE-2026-47101 — High (CVSS 8.8): LiteLLM prior to 1.83.14 allows an authenticated internal_user to create API keys with access to routes that their role…
Other CWE-287 (Improper Authentication) vulnerabilities
- CVE-2026-45480 — Critical (CVSS 10.0): Improper authentication in Azure Active Directory allows an unauthorized attacker to elevate privileges over a network.
- CVE-2026-46389 — Critical (CVSS 10.0): UDS Identity Config builds the Keycloak configuration image (realm, plugins, theme, truststore, JARs) consumed by UDS…
- CVE-2026-10611 — Critical (CVSS 10.0): An authentication bypass vulnerability exists in MISP when LDAP mixed authentication is enabled with OTP enforcement.…
- CVE-2026-47280 — Critical (CVSS 10.0): Improper authentication in Azure Resource Manager (ARM) allows an unauthorized attacker to elevate privileges over a…
- CVE-2026-42822 — Critical (CVSS 10.0): Improper authentication in Azure Local Disconnected Operations allows an unauthorized attacker to elevate privileges…
- CVE-2026-20182 — Critical (CVSS 10.0): May 2026: This security advisory provides the details and fix information for a vulnerability that was discovered and…
Browse all CWE-287 (Improper Authentication) vulnerabilities →