CVE-2026-37004

Unknown

Published: 27/08/2026(UTC)Translated: 28/08/2026(UTC)NVD NIST

Summary

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

Risk Assessment

An attacker can execute arbitrary commands on the server, potentially leading to full system compromise, data theft, or service disruption.

Recommendation

Update litellm to a patched version. Use a sandboxed template environment and validate input before processing.

Original NVD description (English source)

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 dotprompt_content parameter in the /prompts/test endpoint due to use of an unsandboxed jinja2.Environment.