ToolsCVE trackerATT&CKLeak trackerCIDRDNSEmail securityHeadersTrackersTLSMy connectionCSP builderEmail headersJWTCert decoderPassphrasePassword checkHash & encodesecurity.txtDNSSEC & CAA

d4 · tools · cve

CVE-2026-59822.

Severity, exploit probability and exploitation status for one vulnerability, drawn from NVD, FIRST EPSS and CISA's exploited catalogue.

← back to the CVE tracker

known exploited BerriAI LiteLLM Improper Authentication Vulnerability

Vendor / product
BerriAI - LiteLLM
Listed by CISA
2026-09-02
Federal fix deadline
2026-09-16 (1 day away)
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.

Scores

CVSS 4.0
8.8 high 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:
EPSS
0.87% estimated probability of exploitation in the next 30 days (higher than 57% of all CVEs)
Weakness class
CWE-287, CWE-306

ATT&CK techniques

inferred from weakness class no curated mapping exists for this CVE; these are the techniques typically seen with CWE-287, CWE-306 vulnerabilities

ReconnaissanceResource DevelopmentInitial AccessExecutionPersistencePrivilege EscalationStealthDefense ImpairmentCredential AccessDiscoveryLateral MovementCollectionCommand and ControlExfiltrationImpact

T1078 Valid Accounts

Initial AccessPersistencePrivilege EscalationStealth

Adversaries may obtain and abuse credentials of existing accounts as a means of gaining Initial Access, Persistence, Privilege Escalation, or Defense Evasion.

Inferred from CWE-287.

T1190 Exploit Public-Facing Application

Initial Access

Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.

Inferred from CWE-287, CWE-306.

T1059 Command and Scripting Interpreter

Execution

Adversaries may abuse command and script interpreters to execute commands, scripts, or binaries.

Inferred from CWE-287, CWE-306.

T1505 Server Software Component

Persistence

Adversaries may abuse legitimate extensible development features of servers to establish persistent access to systems.

via sub-technique T1505.003 Web Shell

Inferred from CWE-287.

T1068 Exploitation for Privilege Escalation

Privilege Escalation

Adversaries may exploit software vulnerabilities in an attempt to elevate privileges.

Inferred from CWE-287.

T1134 Access Token Manipulation

Privilege EscalationStealth

Adversaries may modify access tokens to operate under a different user or system security context to perform actions and bypass access controls.

Inferred from CWE-287.

T1040 Network Sniffing

Credential AccessDiscovery

Adversaries may passively sniff network traffic to capture information about an environment, including authentication material passed over the network.

Inferred from CWE-287.

T1105 Ingress Tool Transfer

Command and Control

Adversaries may transfer tools or other files from an external system into a compromised environment.

Inferred from CWE-287.

See these techniques on the full ATT&CK matrix.

Description

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
2026-07-08
Last modified
2026-09-03
NVD status
Analyzed

References

Covered in Decrypted

CVSS measures how bad exploitation would be; EPSS estimates how likely exploitation is within 30 days; the CISA listing means it is already happening. Read them together: a CVSS 9.8 with EPSS 0.04% is usually less urgent than a CVSS 7.2 on the exploited list. Data: NVD, FIRST EPSS, CISA KEV; detail is cached for a week, scores for a day. ATT&CK techniques come from the CTID KEV mappings project where a curated mapping exists, otherwise they are inferred from the weakness class and labelled as such. ATT&CK is a registered trademark of The MITRE Corporation. © 2026 The MITRE Corporation. This work is reproduced and distributed with the permission of The MITRE Corporation.