LiteLLM: Server-Side Template Injection in /prompts/test endpoint
Summary
| CVE | CVE-2026-42203 |
|---|---|
| State | PUBLISHED |
| Assigner | GitHub_M |
| Source Priority | CVE Program / NVD first with legacy fallback |
| Published | 2026-05-08 04:16:19 UTC |
| Updated | 2026-06-30 03:19:34 UTC |
| Description | LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process. The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user could reach it. Depending on how the proxy is deployed, this could expose secrets in the process environment (such as provider API keys or database credentials) and allow commands to be run on the host. This issue has been patched in version 1.83.7. |
Risk And Classification
Primary CVSS: v4.0 8.6 HIGH from [email protected]
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/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:X/V:X/RE:X/U:X
EPSS: 0.003730000 probability, percentile 0.293290000 (date 2026-07-03)
Problem Types: CWE-1336 | CWE-94 | CWE-1336 CWE-1336: Improper Neutralization of Special Elements Used in a Template Engine | CWE-94 Improper Control of Generation of Code ('Code Injection')
| Version | Source | Type | Score | Severity | Vector |
|---|---|---|---|---|---|
| 4.0 | [email protected] | Secondary | 8.6 | HIGH | CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/C... |
| 4.0 | CNA | DECLARED | 8.6 | HIGH | CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N |
| 3.1 | [email protected] | Primary | 8.8 | HIGH | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H |
| 3.1 | ADP | CVSS | 8.8 | HIGH | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H |
| 3.1 | 0b0ca135-0b70-47e7-9f44-1890c2a1c46c | Secondary | 8.8 | HIGH | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H |
CVSS v4.0 Breakdown
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/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:X/V:X/RE:X/U:X
CVSS v3.1 Breakdown
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
NVD Known Affected Configurations (CPE 2.3)
Vendor Declared Affected Products
| Source | Vendor | Product | Version | Platforms |
|---|---|---|---|---|
| CNA | BerriAI | Litellm | affected >= 1.80.5, < 1.83.7 | Not specified |
| ADP | Red Hat | Red Hat Ansible Automation Platform 2 | Not specified | Not specified |
| ADP | Red Hat | Exploit Intelligence | Not specified | Not specified |
| ADP | Red Hat | Red Hat OpenShift AI RHOAI | Not specified | Not specified |
References
| Reference | Source | Link | Tags |
|---|---|---|---|
| github.com/BerriAI/litellm/security/advisories/GHSA-xqmj-j6mv-4862 | [email protected] | github.com | Mitigation, Patch, Vendor Advisory |
| access.redhat.com/security/cve/CVE-2026-42203 | 0b0ca135-0b70-47e7-9f44-1890c2a1c46c | access.redhat.com | |
| bugzilla.redhat.com/show_bug.cgi | 0b0ca135-0b70-47e7-9f44-1890c2a1c46c | bugzilla.redhat.com | |
| security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-42203.json | 0b0ca135-0b70-47e7-9f44-1890c2a1c46c | security.access.redhat.com | |
| github.com/BerriAI/litellm/releases/tag/v1.83.7-stable | [email protected] | github.com | Product, Release Notes |
| CVE Program record | CVE.ORG | www.cve.org | canonical |
| NVD vulnerability detail | NVD | nvd.nist.gov | canonical, analysis |
Additional Advisory Data
| Source | Time | Event |
|---|---|---|
| ADP | 2026-05-08T04:01:50.142Z | Reported to Red Hat. |
| ADP | 2026-05-08T03:36:58.648Z | Made public. |
Workarounds
ADP: Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.