GHSA-6wvf-77m9-58rmCriticalCVSS 9.8
LiteLLM vulnerable to server-side template injection in the /prompts/test endpoint
🔗 CVE IDs covered (1)
📋 Description
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.
🎯 Affected products1
- pip/litellm:< 1.83.7
🔗 References (6)
- https://nvd.nist.gov/vuln/detail/CVE-2026-37004
- https://github.com/BerriAI/litellm/blob/244bdffd1bfe7bebdfdef516e1ebe426a898e2f0/litellm/proxy/prompts/prompt_endpoints.py#L1073
- https://yerangamage.com/cves/detail/?slug=litellm-ssti-rce
- https://github.com/BerriAI/litellm/commit/d910a95661fce3cdd36f3b06c03ecf9c46c6457c
- https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable
- https://github.com/advisories/GHSA-6wvf-77m9-58rm