Vulnerability report

Exploited in the wild Confirmed confidence In CISA KEV

CVE-2026-42208

LiteLLM: SQL injection in Proxy API key verification

BerriAI / litellm · All versions (default: unaffected)

Watch CVE-2026-42208 Browse KEV feed
Severity
CVSS 9.3 · Critical
Confidence
Confirmed
Exploit status
Exploited in the wild
EPSS
5.8%
First observed
—
Last observed
—

Decision summary

What security teams need to know first

Direct answers before the deeper technical record.

What it is

CVE-2026-42208 is an unauthenticated LiteLLM: SQL injection in Proxy API key verification. LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before version...

Is it exploited?

Yes. Previdian tracks this CVE as a known exploited vulnerability. Confidence is confirmed. Listed in CISA KEV. Also confirmed by third-party sources.

Who is affected?

BerriAI / litellm all versions (default: unaffected).

What should we do?

Prioritize remediation. Validate affected assets and apply vendor fixes on an accelerated timeline.

Overview

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format

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.

Red Hat Unaffected
All versions (default: unaffected)
Red Hat Unaffected
Red Hat Ansible Automation Platform 2 ansible-automation-platform-26/lightspeed-chatbot-rhel9
All versions (default: unaffected)
Red Hat Unaffected
Red Hat OpenShift AI (RHOAI) rhoai/odh-llama-stack-core-rhel9
All versions (default: unaffected)
Red Hat Unaffected
Red Hat OpenShift AI (RHOAI) rhoai/odh-mlflow-rhel9
All versions (default: unaffected)
BerriAI Affected
litellm
>= 1.81.16, < 1.83.7
Published
08 May 2026
Exploitation Reported
01 Jun 2026
Attack vector
Remote
Complexity
Low
Privileges
None
User interaction
None

Tags

cisa nuclei_scanner

CVE References

Exploitation evidence

Why Previdian marks this CVE as exploited

Third-party attestation and first-party sensor observation are shown separately so teams can judge the evidence chain.

Exploited in the wild

CVE

Recorded 01 Jun 2026

A trusted third party reported exploitation.

Proof of concept available

Nuclei Templates

Recorded 12 Jun 2026

Public scanner or PoC coverage increases practical exploitability.

Known exploited vulnerability sources

Per-source evidence links for KEV attestations are available through the Previdian Pro API.

Learn about Pro API access
Source Added
CVE First 2026-06-01 13:26 UTC
CISA 2026-06-02 14:01 UTC

Detection

Operational artifacts and observed signals

Make the evidence actionable in scanner, SOC, and edge-control workflows.

Observed signals

Request targets
User-Agents
Callback hosts
0
0
0

Request targets and User-Agents available in Pro. Callback host details available in Enterprise.

Virtual patch status

No Previdian virtual patch is currently available. Future rules ship for ModSecurity, Cloudflare, and AWS WAF.

Learn about virtual patches →

Scanner Artifacts

Scanner and exploit-framework references linked to this CVE.

Scanner Reference Detected
Nuclei https://github.com/projectdiscovery/nuclei-templates/blob/main/http/cves/2026/CVE-2026-42208.yaml 01 Jun 2026

Risk and context

Severity, weaknesses, and research context

CVSS v4.0

9.3 Critical

Potential damage if exploited. Separate from whether attackers are using it.

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

EPSS

5.8%

Estimated chance of exploitation in the next 30 days. Previdian's warning comes from evidence, not this score.

Weaknesses

Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection') CWE-89

Recent mention · Github Advisory Database (PIP)

[semantic-router] semantic-router exposed to compromised litellm wheel (CVE-2026-42208) via unbounded transitive pin

Impact semantic-router versions 0.1.8 through 0.1.14 declare litellm>=1.61.3 with no upper bound. During the window in which litellm==1.82.8 was the latest release on PyPI, a fresh install of any affected semantic-router version could resolve to that compromised wheel. The...

Read full advisory

All CVSS Scores

CVSS v4.0 9.3 Critical

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

CVSS v3.1 9.8 Critical

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

All Mentions

Recent mention · Github Advisory Database (PIP)

[semantic-router] semantic-router exposed to compromised litellm wheel (CVE-2026-42208) via unbounded transitive pin

Github Advisory Database (PIP) · 26 Jun 2026

Impact semantic-router versions 0.1.8 through 0.1.14 declare litellm>=1.61.3 with no upper bound. During the window in which litellm==1.82.8 was the latest release on PyPI, a fresh install of any affected semantic-router version could resolve to that compromised wheel. The malicious litellm==1.82.8 wheel ships a litellm_init.pth file that executes on Python interpreter startup — no import required. It collects and exfiltrates: Process environment variables AWS / GCP / Azure credentials SSH keys, Kubernetes configs, shell history Database credentials and CI/CD secrets Cryptocurrency...

Recent mention · Rapid7

Weekly Metasploit Update: Modules for Audiobookshelf, LiteLLM, Next.js, Dalfox and more

Rapid7 · 26 Jun 2026

Help shape the future of Metasploit FrameworkWe are planning future work in relation to the evasion capabilities present in Metasploit Framework, and how they function/are presented to users. We are currently accepting responses to our feedback form, which means that you can shape the future of how evasive capabilities are implemented in Metasploit Framework. The proposal for the changes can be found here, and you can submit your responses to the form here. The form will stop accepting responses on the 1st of July, 2026.New module content and improvements have also been added this week....

Potential Proof of Concepts

These PoCs are unverified and could contain malware. Use at your own risk.

LiteLLM - SQL Injection

nuclei · Created Unknown

Timeline

From disclosure to observed exploitation

  1. 14:21 UTC

    Public PoC available

    Public proof-of-concept code published

  2. 14:01 UTC

    Added to CISA KEV

    Listed in the CISA Known Exploited Vulnerabilities catalog

  3. 15:34 UTC

    Nuclei template available

    Scanner coverage available

  4. 13:26 UTC

    Added to Previdian KEV Feed

    High-confidence, third-party attested exploitation

  5. 03:38 UTC

    CVE published

    Vulnerability disclosed publicly

  6. 05:04 UTC

    CVE ID reserved

    Identifier reserved by the CNA

Pro API

Automate this intelligence

Confidence, exploit status, sensor telemetry, PoCs, scanner integrations, mentions, and tags are available programmatically for VM, SOC, and CTI workflows.

Start 14-day Pro trial Read API docs
  • Evidence confidence and provenance
  • First-party sensor telemetry
  • PoC and scanner references
  • Affected versions and enrichment
  • Automation-ready JSON delivery

GET /api/v2/pro/kevs/CVE-2026-42208

Free JSON includes basic KEV fields 
{
  "cve_id": "CVE-2026-42208",
  "confidence": "Confirmed",
  "cvss_score": 9.3,
  "cvss_estimated": false,
  "epss_score": 0.05772,
  "exploit_status": {
    "exploited_in_the_wild": true,
    "active_exploitation_observed": false
  },
  "sensor_telemetry": { "attempts": 0, "sensors": 0 }
}