What is CVE-2026-59822?

CVE-2026-59822 is LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback. The supplied enrichment data classifies it as Auth Bypass mapped to CWE-287 Improper Authentication; CWE-306 Missing Authentication for Critical Function.

Which versions are affected?

Affected product and version evidence is listed in the product table above. Current public advisories should be checked for exact version scope before patch targeting is finalized.

Is there active exploitation?

Yes: CISA KEV signal present. If exploitation is not confirmed from current sources, teams should document that status and continue monitoring KEV, vendor, and telemetry updates.

Is there a public exploit?

10 public PoC repositories reported; 3 marked weaponized in current dataset. Public exploit or PoC availability should raise triage priority, especially for exposed or business-critical systems.

How can defenders detect it?

Start with web/proxy/WAF logs, application logs, network IDS/IPS, identity provider logs, authentication audit logs where available. Look for vulnerability-class behavior, product errors, suspicious authentication events, exploit probes, and abnormal process activity based only on evidence that applies to the affected product.

How should teams prioritize it?

Prioritize CVE-2026-59822 using CVSS 8.2, EPSS 1%, KEV status, public PoC status, and asset exposure. Internet-facing, privileged, or business-critical deployments should be handled first.

Are workarounds available?

Workarounds are not confirmed from current sources. Fixed-version evidence is listed in the mitigation section above.

Which threat actors are linked publicly?

Publicly linked actor or ransomware signals in the supplied enrichment data: APT 28 (), Awaken Likho (), Tortoiseshell (). Do not attribute exploitation to a threat actor unless the source evidence explicitly supports that linkage.

What should be done in the next 24 hours?

Identify exposed assets running affected vendor/product/version combinations. Treat as emergency remediation because CISA KEV status is present. Search available logs for exploit probes, errors, authentication anomalies, or suspicious child processes matching the vulnerability class. Open remediation tickets with affected assets, owners, evidence status, and detection coverage so decisions are traceable.

CISA KEVhighAuth Bypasspublic exploit

CVE-2026-59822

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

Q: Is it in CISA KEV?

Yes. The supplied enrichment data lists CVE-2026-59822 in CISA KEV with required action: Apply mitigations in accordance with vendor instructions, ensuring compliance with CISA’s BOD 26-04 Prioritizing Security Updates Based on Risk (see URL in Notes) guidance and CISA’s “Forensics Triage Requirements” (see URL in Notes). Follow applicable BOD 26-04 guidance for cloud services or discontinue use of the product if mitigations are unavailable. Stakeholders are responsible for evaluating each asset's internet exposure and ensuring adherence to BOD 26-04 patching guidelines.. KEV status should be monitored because it can change after initial disclosure or after exploitation becomes publicly confirmed.

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.

Published Jul 8, 2026Updated Sep 2, 2026Sources: NVD, BerriAI (CNA), CISA, FIRST EPSS, GitHub, GitHub Security Advisory, Red Hat (VEX), SOCRadar CTI

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the scoring sources call it.

Exploitation

Confirmed

CISA KEV, listed Sep 2, 2026

EPSS

ahead of 57% of scored CVEs

Affects

BerriAI

2 products listed

CVSS base

8.2

high · 2 sources

CISA SSVC assessment

Three decision points CISA publishes for the CVEs it assesses · SSVC 2.0.3. A stakeholder decision, not a severity score.

CISA

Exploitation

Active

none · proof-of-concept · active

Automatable

Yes

can an attacker script all four kill-chain steps

Technical impact

Partial

partial · total control of the vulnerable component

Remediation

The vendor's own words where we have them.

Upgrade litellm to 1.84.0 or later (pip advisory GHSA-7488-6r32-c95q).

CISA required action

Apply mitigations in accordance with vendor instructions, ensuring compliance with CISA’s BOD 26-04 Prioritizing Security Updates Based on Risk (see URL in Notes) guidance and CISA’s “Forensics Triage Requirements” (see URL in Notes). Follow applicable BOD 26-04 guidance for cloud services or discontinue use of the product if mitigations are unavailable. Stakeholders are responsible for evaluating each asset's internet exposure and ensuring adherence to BOD 26-04 patching guidelines.

Federal deadline Sep 16, 2026 — passed 8 days ago

Red Hat VEX · CVE-2026-59822

fixed0affected0not affected1

First 24 hours

Ordered from the record's own fields — exposure first, because you cannot patch what you have not found.

Identify exposed assets running affected vendor/product/version combinations.
Treat as emergency remediation because CISA KEV status is present.
Search available logs for exploit probes, errors, authentication anomalies, or suspicious child processes matching the vulnerability class.

Affected scope

Vendor, product and version as the advisories word them.

Vendor	Product	Versions	Status
BerriAI	litellm	< 1.84.0	Vulnerable
pip	litellm	< 1.84.0	Vulnerable

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Availability

None

Confidentiality

High

Integrity

Low

Scope

Unchanged

Attack Complexity

Low

Attack Vector

Network

Privileges Req

None

User Interaction

None

Every base score collected

Sources score independently and disagree; each row says who scored it and under which version.

Score	Version	Severity	Expl.	Impact	Source
8.2	CVSS 3.1	high	3.9	4.2	NVD, Red Hat (VEX)
8.8	CVSS 4.0	high	—	—	BerriAI (CNA)

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N

What this weakness leads to

MITRE's own consequences and mitigations for the weakness class — the authority's wording, not guidance derived from the CVSS vector.

MITRE

CWE-287 · Improper Authentication

Read Application Data
Gain Privileges or Assume Identity
Execute Unauthorized Code or Commands

Mitigation: Use an authentication framework or library such as the OWASP ESAPI Authentication feature.::

CWE-306 · Missing Authentication for Critical Function

Gain Privileges or Assume Identity
Other

Mitigation: Divide the software into anonymous, normal, privileged, and administrative areas. Identify which of these areas require a proven user identity, and use a centralized authentication capability. Identify all potential communication channels, or other means of interaction with the software, to ensure that all channels are appropriately protected. Developers sometimes perform authentication at the primary channel, but open up a secondary channel that is assumed to be private. For example, a login mechanism may be listening on one network port, but after successful authentication, it may open up a second port where it waits for the connection, but avoids authentication because it assumes that only the authenticated party will connect to the port. In general, if the software or protocol allows a single session or user state to persist across multiple connections or channels, authentication and appropriate credential management need to be used throughout.

Weakness & attack patterns

CWE-287Improper Authentication
CWE-306Missing Authentication for Critical Function

Attack patterns reported against this CVE. The ATT&CK techniques below are inferred from its weakness class.

CAPEC-151 · Identity SpoofingCAPEC-57 · Utilizing REST's Trust in the System Resource to Obtain Sensitive DataCAPEC-194 · Fake the Source of DataCAPEC-22 · Exploiting Trust in ClientCAPEC-650 · Upload a Web Shell to a Web ServerCAPEC-593 · Session HijackingCAPEC-114 · Authentication AbuseCAPEC-94 · Man in the Middle AttackCAPEC-633 · Token ImpersonationCAPEC-115 · Authentication Bypass

T1548Abuse Elevation Control Mechanism
T1040Network Sniffing
T1185Browser Session Hijacking

CISA KEV details

CISA lists a CVE here once it has evidence of exploitation against real targets.

CISAThat month →

Listed

Sep 2, 2026

Federal deadline

Sep 16, 2026

passed 8 days ago

Ransomware use

Unknown

CISA records ransomware use only for campaigns it has confirmed, so “Unknown” means unrecorded, not ruled out. The deadline binds US federal agencies; for everyone else it is a date to argue against.

Public exploit

Capability, not use: code existing is a different claim from anyone running it.

Repositories

3 of the 5 sampled are weaponized

Social mentions

Posts naming this CVE. Attention, not evidence of exploitation — it spikes on disclosure and decays whether or not anything is exploited.

Detection

Read off the CVSS vector and the weakness class. Starting points, not rules we have tested.

Prioritize edge telemetry for network-reachable litellm.
Monitor for scanner or exploit-pattern traffic after 10 public PoC repositories were reported.

web/proxy/WAF logsapplication logsnetwork IDS/IPSidentity provider logsauthentication audit logs

Groups associated with this CVE

Groups reported in connection with this vulnerability. A reported association, not a confirmed observation of that group using it — and not scoped to any sector or campaign.

APT 28Awaken LikhoTortoiseshell

ip185.84.98.8594
AlienVault OTX Feeds · Feb 2, 2026
ip185.62.1.877
iocradar0-netizen - Public_News - Feed · Jul 11, 2026
hostnamecrazyeltonproxy.top48
AlienVault OTX Feeds · Aug 28, 2026
urlhttp://185.62.1.8/mon/mon.zip'56
Threatview.io Feeds · Aug 29, 2026

Timeline

What happened to this CVE, newest first — with the readings a source repeats on a schedule counted underneath rather than listed.

2026
Added to CISA KEV catalog
Sep 2, 2026 · CISA
Added · CVSS 3.1 8.2 (AV:N)
Sep 2, 2026 · NVD
Added · GHSA-7488-6r32-c95q published (high)
Jul 22, 2026 · GitHub Security Advisory
Initial · CVE published
Jul 8, 2026 · NVD

Source activity

Readings a source repeats on a schedule, counted rather than listed.

5×Tweets · 1 time tweeted.Jul 14, 2026 – Sep 2, 2026 · SOCRadar CTI
1×CVE appeared in the Cve Trends.Aug 29, 2026 · SOCRadar CTI
1×SVRS is calculatedAug 29, 2026 · SOCRadar CTI
1×CVE modified by MITRE: CVSS metrics updated.Jul 8, 2026 · SOCRadar CTI

References

12 on the record

github.com/BerriAI/litellm/commit/73869f0faf7d11ee21adcb5f91b8c33a340b6c2c
Patch, NIST, Mitre
github.com/BerriAI/litellm/pull/26463
Issue Tracking, Patch, NIST, Mitre
github.com/BerriAI/litellm/releases/tag/v1.84.0
Product, Release Notes, NIST, Mitre
github.com/BerriAI/litellm/security/advisories/GHSA-7488-6r32-c95q
Mitigation, Patch, Vendor Advisory, NIST, Mitre
www.cisa.gov/known-exploited-vulnerabilities-catalog?field_cve=CVE-2026-59822
US Government Resource
www.wiz.io/blog/ai-infrastructure-honeypot
Third Party Advisory, NIST, GITHUB
nvd.nist.gov/vuln/detail/CVE-2026-59822
NVD, Vendor Advisory
github.com/advisories/GHSA-7488-6r32-c95q
Exploit, Third Party Advisory

Coverage

4 stories from the feeds we poll

Elsewhere on this site

BerriAIevery CVE for this vendor
pipevery CVE for this vendor
September 2026what else CISA listed
Auth Bypasssame class
CWE-287other pages naming this weakness

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

Only the 4 indicator(s) reported for this CVE are available; no packet-level or host-forensic artifacts supplied.
No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record1

What should defenders know first?

CVE-2026-59822 is LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback, a high vulnerability affecting litellm from BerriAI, pip. The current evidence lists it in CISA KEV, and the exploit status is: Yes: CISA KEV signal present. Public exploit evidence is: 10 public PoC repositories reported; 3 marked weaponized in current dataset. The affected-version evidence is listed in the key facts and affected products tables. Defenders should first verify whether exposed or business-critical assets run those versions, then apply vendor patches or mitigations, restrict reachable attack surface, and preserve logs for detection review. CVSS 8.2 describes technical severity, while EPSS 1% helps estimate near-term exploit likelihood; neither replaces asset context. Unknown fields should remain explicit in tickets, and threat actor, IOC, victimology, or payload claims should not be added unless a cited source supports them. Monitor CISA KEV, vendor advisories, NVD changes, public PoC repositories, and internal telemetry for update triggers.