LiveActive security incident?Get immediate response
CVE Record

CVE-2026-35030: LiteLLM has an authentication bypass via OIDC userinfo cache key collision

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.

CriticalCVSS 9.4Not KEV-listedUpdated
Discuss exposureBack to CVEs
Glexia's TakeAutomated analysiscritical

Security readout for executives and security teams

Plain-English summary

CVE-2026-35030 lets an unauthenticated attacker be treated as another user in specific LiteLLM gateway deployments. The risky setup is JWT/OIDC authentication enabled on versions before 1.83.0. Most instances are reportedly not affected because this option is off by default.

Executive priority

Treat as urgent for affected LiteLLM AI gateways because it can bypass authentication and inherit another user's permissions. Reduce priority only after confirming JWT/OIDC authentication is disabled or the deployment is upgraded.

Technical view

Prior to LiteLLM 1.83.0, the OIDC userinfo cache key used only the first 20 token characters. Tokens sharing that prefix could collide, causing cached userinfo for a legitimate user to be reused and granting that user's identity and permissions.

Likely exposure

Exposure is limited to BerriAI LiteLLM versions below 1.83.0 with enable_jwt_auth: true and OIDC userinfo caching in use. Deployments using defaults without JWT authentication are described as generally unaffected.

Exploitation context

The bundle does not cite active exploitation, and KEV is false. Exploitation requires a cache-hit condition against a legitimate user's cached token context, but no public exploit status is provided in the supplied sources.

Researcher notes

The core weakness is a cache-key collision caused by truncating JWT-derived cache keys. The source bundle identifies CWE-222 and CWE-287, CVSS 4.0 score 9.4, and a fix in 1.83.0, but does not provide exploit telemetry.

Mitigation direction

  • Upgrade LiteLLM to version 1.83.0 or later.
  • Confirm whether enable_jwt_auth is enabled in LiteLLM configuration.
  • Prioritize internet-facing or multi-tenant LiteLLM gateways.
  • Review Red Hat advisories if consuming LiteLLM through Red Hat packages.
  • If upgrade is delayed, check vendor guidance for supported interim controls.

Validation and detection

  • Inventory all LiteLLM deployments and record running versions.
  • Inspect configuration for enable_jwt_auth: true.
  • Confirm whether OIDC/JWT authentication is used in production paths.
  • Review gateway logs for unexpected identity switches or permission mismatches.
  • Verify patched systems report LiteLLM 1.83.0 or later.
Prepared
Confidence
high
Sources
9

Public sources used

Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.

Potential ATT&CK relevance

Conservative CVE-to-ATT&CK context

These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.

ATT&CK lookup starting points

Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.

cwe · low confidence lookup

CWE-222: Exact CWE lookup

Use the exact CWE identifier as the starting point before reviewing related ATT&CK behavior. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.

Open ATT&CK lookup
cwe · medium confidence lookup

CWE-287: Credential and account abuse lookup

Authentication and credential weaknesses can make valid-account abuse and credential telemetry useful review starting points. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.

Open ATT&CK lookup
description · low confidence lookup

Credential and access behavior lookup

The CVE wording references authentication or credential exposure, so valid-account and credential-access review may help. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.

Open ATT&CK lookup
cve · low confidence lookup

CVE-2026-35030 mapping review

Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.

Open ATT&CK lookup
Vulnerability profileCVE Program record
Severity
Critical
CVSS
9.4 (4.0)
Known Exploited
No
Published

Vector: 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

Official CVE source material

CNA and ADP enrichment extracted from CVE v5

These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.

3CVSS vectors
5Timeline events
2ADP providers
8Source links

SSVC decision data

CISA-ADPCISA Coordinator
Timestamp
Version
2.0.3
Exploitation: noneAutomatable: yesTechnical Impact: total

CVSS vector scores

3 official scores

We collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.

ScoreVersionSeverityVectorExploitImpactSource
9.4CVSS 4.0CriticalCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:N/SC:H/SI:H/SA:N——GitHub_M
9.1CVSS 3.1CriticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N3.95.2CISA-ADP
9.1CVSS 3.1CriticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N3.95.2redhat-SADP

Vulnerability scoring details

Base CVSS 4.0 score

9.4Critical
CVSS 4.0 vector shape for CVE-2026-35030Attack VectorAttack ComplexityAttack RequirementsPrivileges RequiredUser InteractionVS ConfidentialityVS IntegrityVS AvailabilitySS ConfidentialitySS IntegritySS Availability

Vector: 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

Attack Vector
NetworkAdjacentLocalPhysical
Attack Complexity
LowHigh
Attack Requirements
NonePresent
Privileges Required
NoneLowHigh
User Interaction
NonePassiveActive
VS Confidentiality
HighLowNone
VS Integrity
HighLowNone
VS Availability
HighLowNone
SS Confidentiality
HighLowNone
SS Integrity
HighLowNone
SS Availability
HighLowNone

Vulnerability timeline

Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.

  1. CVE reservedCVE Program

    The CVE ID was reserved by the assigning CNA.

  2. ADP timelineredhat-SADP

    Made public.

  3. CVE publishedCVE Program

    The CVE record was published.

  4. ADP timelineredhat-SADP

    Reported to Red Hat.

  5. CVE updatedCVE Program

    The CVE record metadata indicates this as the latest update time.

ADP provider summaries

CISA-ADPCISA ADP Vulnrichment
cvssV3_1other:ssvc
redhat-SADPlitellm: LiteLLM: Authentication bypass and privilege escalation via OIDC userinfo cache key collision
other:Red Hat severity ratingcvssV3_1
  • 2026-04-06T18:01:07.517Z: Reported to Red Hat.
  • 2026-04-06T16:47:02.065Z: Made public.

Source materials

Affected products

Products and packages named in the record

VendorProductVersion / packageStatus
BerriAIlitellm< 1.83.0Listed
Weakness

CWE details

CWE-222CWE-287

CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.

CWE-222 · source CWE mapping

Truncation of Security-relevant Information

Truncation of Security-relevant Information represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.

Open CWE intelligenceSame-CWE CVEs
CWE-287 · source CWE mapping

Improper Authentication

Improper Authentication represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.

Open CWE intelligenceSame-CWE CVEs