Skip to content
Noroxi
NVD / CVE Program· CNA GitHub_M

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

CriticalCVSS 9.4 · v4.0—Proof of concept Fix available

Noroxi assessment

Priority: Monitor (action score 37/100)

  • Public proof-of-concept code exists (GitHub); there is no record of exploitation in the wild.
  • Probability of exploitation in the next 30 days: 0.63% (FIRST EPSS); higher than 50.9% of all records.
  • Anyone who can reach it over the internet can trigger it. No account or password is required. No user action is required. No special conditions are required; it is repeatable.
  • According to CISA the attack is automatable: targets can be found by mass scanning.
  • Fixed version: litellm (PyPI) 1.83.0.

Low priority for now. Upgrade to litellm (PyPI) 1.83.0 or later.

Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it

Primary sources: NVD · CVE.org · FIRST EPSS

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.

Published
Apr 6, 2026
Updated
Oct 24, 2026
EPSS
0.6% · 50th percentile

Report tools

JSON

Action score

37

Monitor

Low priority for now.

CVSS
37 / 40 · 9.4 / 10
CISA KEV
0 / 30 · Not listed
EPSS
0 / 30 · 0.6%

CISA SSVC decision

Exploitation
none
Automatable
yes
Technical impact
total

Vulnrichment: CISA's decision-tree inputs.

CNA vs NVD score

NVD
—
CNA · GitHub_M
9.4
NVD has not scored this yet; the score shown is the CNA’s.

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

The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.

Get told when this record changes

  • Not in KEV: no record of exploitation in the wild
  • Proof of concept exists, no weaponized module
  • A fix has been released

If any of these changes, we'll tell you in the daily email digest.

Follow CVE-2026-35030

When you'll hear from us

  • when it enters CISA KEV
  • when exploit code appears or is weaponized
  • when the record is updated (including a fixed version)
  • when EPSS rises 20 points in a week

One daily email digest (06:00 UTC); connect a webhook for KEV listings and weaponized exploits every 10 minutes on paid plans, on the hour on the free plan.

Your free account also gets you

  • CVE alerts: add the products and versions you run, get the new CVEs that affect them
  • Uptime monitoring: 1 site, instant email when it goes down
  • Add your domain: subdomains and takeover risk scanned every week (1 domain)
  • 10 scans an hour on the security tools, at most 30 a day (3 a day without an account), an API key and MCP
  • All your scans in one panel: findings, what changed in the last scan, a report per domain or per client (PDF, share link)
All free tools

Sign up with email · Have an account? Sign in

Free account, no card. Unfollow any time.

Don't want an account? Get "Exploited this week" by email every MondayDon't want an account? RSS feed for litellm records
Is your version affected? Check it

Noroxi analysis

What does it mean in your environment?

The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.

We use this product, ask for help

Affected systems

Is your version affected?

Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.

VendorProduct
litellmlitellm

Versions reported by the vendor

Affected version ranges reported by the assigning authority (GitHub_M). Independent of NVD's CPE analysis and usually ahead of it.

  • BerriAI litellm

    • < 1.83.0affected

Affected versions

NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.

  • litellm litellmbefore 1.83.0

Package-level exposure

OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.

EcosystemPackageAffected rangeFix
PyPIlitellmbefore 1.83.01.83.0

Same product

litellm: all records

Other highest-scoring records for the same primary product.

  • CVE-2026-42208LiteLLM: SQL injection in Proxy API key verificationKEV
    94Now
  • CVE-2026-42271LiteLLM: Authenticated command execution via MCP stdio test endpointsKEV
    91Now
  • CVE-2026-59822LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough FallbackKEV
    65This week

Published before and after this one in the same product

  • ← EarlierCVE-2025-11203Oct 29, 2025 · LiteLLM Information health API_KEY Information Disclosure Vulnerability
    14Monitor
  • ← EarlierCVE-2026-35029Apr 6, 2026 · LiteLLM affected by privilege escalation via unrestricted proxy configuration endpoint
    46Plan
  • Later →CVE-2026-40217Apr 10, 2026 · LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /guardrails/test_custom_code URI.
    40Plan

Remediation

Which version to upgrade to

Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.

Product / packageFixed versionSource
PyPI:litellm1.83.0Package registry (OSV)

Exploit status

Proof of concept available

A public proof of concept or detection signature exists. Exploit knowledge is out there; don't delay patching.

Evidence

  • Proof-of-concept repository on GitHub ×1

Noroxi does not host or link to exploit code. Metasploit module names and Nuclei template ids are shown (names, not code); Exploit-DB entries and PoC repositories are given as counts only.

Public exploit evidence
SourceKindDate
Proof-of-concept repository on GitHubstars:02026-05-19

Research context

For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.

Timeline

From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.

  1. Published
  2. First PoC+42 d
  3. TodayNov 12, 2026+220 d

Variant candidates

Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.

  • CVE-2026-5982293 days apartLiteLLM: MCP Authentication Bypass via OAuth2 Passthrough FallbackKEV
    65This week
  • CVE-2026-1277376 days apartBerriAI litellm MCP Proxy user_api_key_auth_mcp.py UserAPIKeyAuth improper authentication
    22Monitor
  • CVE-2026-1279576 days apartBerriAI litellm SSO Debug Flow ui_sso.py json.dumps missing authentication
    22Monitor

Chain candidates

An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.

  • CVE-2026-4227132 days apartLiteLLM: Authenticated command execution via MCP stdio test endpointsKEV
    91Now
  • CVE-2026-350290 days apartLiteLLM affected by privilege escalation via unrestricted proxy configuration endpoint
    46Plan
  • CVE-2026-402174 days apartLiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /guardrails/test_custom_code URI.
    40Plan
  • CVE-2026-4220332 days apartLiteLLM: Server-Side Template Injection in /prompts/test endpoint
    34Monitor

Not on record for this CVE: EPSS history · patch commit or PR link · researcher credit · public bounty program.

Technical details

Attack conditions

  • Anyone who can reach it over the internet can trigger it.
  • No account or password is required.
  • No user action is required.
  • No special conditions are required; it is repeatable.

If successful

Confidentiality
Integrity
Availability
Attack vector
Network
Attack complexity
Low
Privileges required
None
User interaction
None
Scope
X

Weakness class (CWE)

CWE-287 · Improper Authentication

CVSS 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

nvd-secondary

Root cause

Authentication is added route by route instead of being enforced in one place. When a route added later bypasses the shared middleware, the session check never runs for it.

The bug in code

The whole CWE-287 class

A representative example of this vulnerability class. Not the vendor's source code; it shows the faulty pattern and its fix.

Vulnerable

ts
app.use("/admin", requireSession, adminRouter);
// Route added later skips the middlewareapp.post("/admin-api/config", updateConfig);

Fixed

ts
const admin = express.Router();admin.use(requireSession, requireRole("admin"));
admin.post("/config", updateConfig);app.use("/admin", admin);

Attack context

MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.

References

Show all references (6 more)

Vendor advisories and official records. Exploit/PoC links are deliberately left out.

All records