NVD / CVE Program· CNA GitHub_M

CVE-2026-59822: LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback

Noroxi assessment

Priority: This week (action score 65/100)

CISA has confirmed exploitation in the wild (Sep 2, 2026). Remediation deadline for US federal agencies: Sep 16, 2026.
Probability of exploitation in the next 30 days: 0.83% (FIRST EPSS); higher than 57.8% 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: BerriAI litellm 1.84.0.
Mentioned 1 time in Turkish national cyber security advisories (siberguvenlik.gov.tr).

Don’t wait for the next maintenance window. Upgrade to BerriAI litellm 1.84.0 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 · CISA KEV · FIRST EPSS

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, LiteLLM's MCP Streamable HTTP endpoint allowed an unauthenticated attacker to use a fabricated Authorization header to trigger an OAuth2 passthrough fallback path that replaced failed LiteLLM key validation with an empty UserAPIKeyAuth() object, allowing requests to reach MCP tooling without a valid LiteLLM key. This issue is fixed in version 1.84.0.

HighCVSS 8.8 · v4.0KEVWeaponized Fix available

Published: Jul 8, 2026
Updated: Oct 25, 2026
EPSS: 0.8% · 57th percentile
CWE: CWE-287

Report tools

JSON

Action score

This week

Don’t wait for the next maintenance window.

CVSS: 35 / 40 · 8.8 / 10
CISA KEV: 30 / 30 · Listed
EPSS: 0 / 30 · 0.8%

CISA SSVC decision

Exploitation: active
Automatable: yes
Technical impact: partial

Vulnrichment: CISA's decision-tree inputs.

CNA vs NVD score

NVD: —
CNA · GitHub_M: 8.8; NVD has not scored this yet; the score shown is the CNA’s.

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:L/VA:N/SC:N/SI:N/SA:N

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

Actively exploited in the wild

CISA added this to its Known Exploited Vulnerabilities catalog on Sep 2, 2026. That signals real attacks, not theory.

Remediation deadline for US federal agencies: Sep 16, 2026.

Get told when this record changes

In CISA KEV: exploitation in the wild confirmed
Weaponized exploit exists
A fix has been released

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

Running WordPress? Scan your site free with WP Lens

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.

Vendor	Product	CPE
litellm	litellm	cpe:2.3:a:litellm:litellm

Affected versions

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

litellm litellmbefore 1.84.0

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
- < 1.84.0affected

Package-level exposure

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

Ecosystem	Package	Affected range	Fix
PyPI	litellm	before 1.84.0	1.84.0

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-2026-35029LiteLLM affected by privilege escalation via unrestricted proxy configuration endpoint
46Plan

Published before and after this one in the same product

← EarlierCVE-2026-59819Jul 8, 2026 · LiteLLM: Local file read via request-supplied OIDC file references
8Monitor
← EarlierCVE-2026-59820Jul 8, 2026 · LiteLLM: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
24Monitor
← EarlierCVE-2026-59821Jul 8, 2026 · LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks
8Monitor

Remediation

Which version to upgrade to

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

Product / package	Fixed version	Source
BerriAI litellm	1.84.0 · description	Vendor (CNA)
PyPI:litellm	1.84.0	Package registry (OSV)

Exploit status

Weaponized

A ready exploit tool or active in-the-wild use is known for this vulnerability. This should be your top priority.

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
Source	Kind	Date
Proof-of-concept repository on GitHub	stars:0	2026-09-03

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.

PublishedJul 8, 2026
CISA KEVSep 2, 2026+55 d
First PoCSep 3, 2026+56 d
TodayNov 6, 2026+121 d

EPSS, last 120 days+1% in 7 days

FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).

Patch and commit links

Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.

Credits

All researchers

Finders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.

No credits in the CNA record.

Variant candidates

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

CVE-2026-3503093 days apartLiteLLM has an authentication bypass via OIDC userinfo cache key collision
37Monitor
CVE-2026-1277317 days apartBerriAI litellm MCP Proxy user_api_key_auth_mcp.py UserAPIKeyAuth improper authentication
22Monitor
CVE-2026-1279517 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-2026-598200 days apartLiteLLM: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
24Monitor
CVE-2026-598190 days apartLiteLLM: Local file read via request-supplied OIDC file references
8Monitor
CVE-2026-598210 days apartLiteLLM: Custom Code Guardrails production endpoints bypass code safety checks
8Monitor
CVE-2026-1277417 days apartBerriAI litellm MCP Server Connection Testing rest_endpoints.py _execute_with_mcp_client server-side request forgery
8Monitor

Bug bounty scope

No known public program.

Source: bounty-targets-data (public HackerOne, Bugcrowd, Intigriti, YesWeHack listings).

National notice (Türkiye Cybersecurity Directorate / USOM)

Official security notices citing this record; remediation advice is on the agency's page.

TR-26-0531 · Jul 13, 2026(LiteLLM Güvenlik Zafiyeti)

All national notices →

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:N/PR:N/UI:N/VC:H/VI:L/VA:N/SC:N/SI:N/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

1app.use("/admin", requireSession, adminRouter);
2

3// Route added later skips the middleware
4app.post("/admin-api/config", updateConfig);

Fixed

1const admin = express.Router();
2admin.use(requireSession, requireRole("admin"));
3

4admin.post("/config", updateConfig);
5app.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.

Attack patterns (CAPEC)

ATT&CK techniques

Change log

Fix✗ → ✓Sep 28, 2026, 10:45 PM UTC

For records you follow, these changes also arrive as notifications. →

References

github.com/BerriAI/litellm/commit/73869f0faf7d11ee21adcb5f91b8c33a340b6c2c

Show all references (5 more)

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

All records