CVE-2026-42203: LiteLLM: Server-Side Template Injection in /prompts/test endpoint

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.

CVSS vector

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

Attack vector

Network

Complexity

Low

Privileges

Low

User interaction

None

Confidentiality

High

Integrity

High

Availability

High

Scope

Unchanged

Exploitation

Is it being used?

Exploit prediction (EPSS)0.4% · higher than 31% of CVEs

Exploited in the wildNo evidence yet

CISA KEVNot listed

Ransomware campaign useNot known

Affected products

Which versions

LI

litellm · BerriAI

>= 1.80.5, < 1.83.7 · source: vendor, NVD

RH

Red Hat Ansible Automation Platform 2 · Red Hat

All versions, or not specified · source: CISA