CVE-2026-37004: LiteLLM vulnerable to server-side template injection in the /prompts/test endpoint
(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 dotprompt_content parameter in the /prompts/test endpoint due to use of an unsandboxed jinja2.Environment.
References
- github.com/BerriAI/litellm/blob/244bdffd1bfe7bebdfdef516e1ebe426a898e2f0/litellm/proxy/prompts/prompt_endpoints.py
- github.com/BerriAI/litellm/commit/d910a95661fce3cdd36f3b06c03ecf9c46c6457c
- github.com/BerriAI/litellm/releases/tag/v1.83.7-stable
- github.com/advisories/GHSA-6wvf-77m9-58rm
- nvd.nist.gov/vuln/detail/CVE-2026-37004
- yerangamage.com/cves/detail/?slug=litellm-ssti-rce
Code Behaviors & Features
Detect and mitigate CVE-2026-37004 with GitLab Dependency Scanning
Secure your software supply chain by verifying that all open source dependencies used in your projects contain no disclosed vulnerabilities. Learn more about Dependency Scanning →