CVE-2026-37004: BerriAI LiteLLM vulnerability

Published Aug 27, 2026
·
Updated

BerriAI litellm <=1.82.4 is vulnerable to Server-Side Template Injection (SSTI), which allows unauthenticated remote attackers to execute arbitrary OS commands via a crafted dotpromptcontent parameter in the /prompts/test endpoint due to use of an unsandboxed jinja2.Environment.

Affected Software

1 affected component
BerriAI LiteLLM<=1.82.4

Event History

Aug 27, 2026
CVE Published
via MITRE·12:00 AM
Data Sourced
via MITRE·12:00 AM
Description
Data Sourced
via NVD·08:17 PM
Description

Frequently Asked Questions

1

Who can exploit this issue?

An unauthenticated remote attacker can exploit it if they can reach the /prompts/test endpoint and submit a crafted dotprompt_content parameter.

2

What is the potential impact of successful exploitation?

Successful exploitation can result in arbitrary operating-system command execution on the affected LiteLLM host.

3

Which LiteLLM versions are affected?

BerriAI LiteLLM versions 1.82.4 and earlier are identified as vulnerable.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203