---
id: CVE-2026-42208
title: >-
  LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native)
  format
summary: >-
  LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native)
  format. From version 1.81.16 to before version 1.83.7, a database query used
  during proxy API key checks mixed the caller-supplied key value into the query
  tex…
severity: critical
cvss: 9.8
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H'
cwe:
  - CWE-89
published: '2026-05-08'
updated: '2026-06-27'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-42208'
references:
  - url: 'https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable'
    label: security-advisories@github.com
  - url: 'https://github.com/BerriAI/litellm/security/advisories/GHSA-r75f-5x8p-qvmc'
    label: security-advisories@github.com
  - url: 'https://access.redhat.com/security/cve/CVE-2026-42208'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://bugzilla.redhat.com/show_bug.cgi?id=2463965'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: >-
      https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-42208.json
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: >-
      https://www.cisa.gov/known-exploited-vulnerabilities-catalog?field_cve=CVE-2026-42208
    label: 134c704f-9b21-4f2e-91b3-4a467353bcc0
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-42208'
  - url: 'https://github.com/BerriAI/litellm'
tags:
  - nvd
  - kev
  - in-the-wild
  - exploit-available
  - osv
  - pip
epss: 0.8942
epssPercentile: 0.99782
kev: true
kevDateAdded: '2026-05-08'
kevDueDate: '2026-05-11'
kevRansomware: false
exploited: true
zeroDay: true
ingestedAt: '2026-06-29T13:24:34.839Z'
exploits:
  github: 6
  githubRepos:
    - 'https://github.com/ridhinva/litellm-sqli-scanner'
    - 'https://github.com/imjdl/CVE-2026-42208_lab'
    - 'https://github.com/0xBlackash/CVE-2026-42208'
  metasploit:
    - auxiliary/scanner/http/litellm_proxy_sqli
  nuclei:
    - CVE-2026-42208
  checkedAt: '2026-09-21T15:28:53.368Z'
exploitAvailable: true
aliases:
  - GHSA-r75f-5x8p-qvmc
  - PYSEC-2026-391
ecosystem: pip
vendor: litellm
product: litellm
affected:
  - 'litellm >= 1.81.16, < 1.83.7'
patched:
  - litellm 1.83.7
---

## Overview

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before version 1.83.7, a database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route (for example POST /chat/completions) and reach this query through the proxy's error-handling path. An attacker could read data from the proxy's database and may be able to modify it, leading to unauthorised access to the proxy and the credentials it manages. This issue has been patched in version 1.83.7.

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.

## Package advisory (CVE-2026-42208)

Affected packages:

- `litellm >= 1.81.16, < 1.83.7`

Patched in:

- `litellm 1.83.7`

Source: https://osv.dev/vulnerability/GHSA-r75f-5x8p-qvmc