CVE-2026-37004: n/a
Description
BerriAI litellm versions up to 1.82.4 are vulnerable to a Server-Side Template Injection (SSTI) flaw. This vulnerability allows unauthenticated remote attackers to execute arbitrary operating system commands by sending a specially crafted dotprompt_content parameter to the /prompts/test endpoint. The root cause is the use of an unsandboxed jinja2.Environment for template rendering. The vulnerability has a critical severity with a CVSS score of 9.8.
CVSS v3.1
Score 9.8critical
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-37004 describes a Server-Side Template Injection vulnerability in BerriAI litellm versions up to 1.82.4. The vulnerability arises because the application uses an unsandboxed jinja2.Environment to process templates, specifically in the /prompts/test endpoint's dotprompt_content parameter. This allows unauthenticated remote attackers to inject and execute arbitrary OS commands on the server, leading to full compromise. The vulnerability is classified under CWE-1336 and has a CVSS v3.1 base score of 9.8, indicating critical impact across confidentiality, integrity, and availability.
Potential Impact
Successful exploitation allows unauthenticated remote attackers to execute arbitrary operating system commands on the affected server. This can lead to complete system compromise, including data theft, service disruption, and further network penetration. The vulnerability affects confidentiality, integrity, and availability with a critical severity rating.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, restrict access to the /prompts/test endpoint and avoid exposing the vulnerable service to untrusted networks. Monitor for unusual activity related to template rendering. Do not rely on generic mitigations as the vulnerability specifically involves unsandboxed template execution.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- mitre
- Date Reserved
- 2026-04-06T00:00:00.000Z
- State
- PUBLISHED
Threat ID: 6a909cefacd9273b49b2cd5e
Added to database: 08/27/2026, 20:24:15 UTC
Last enriched: 09/07/2026, 15:12:40 UTC
Last updated: 10/10/2026, 18:48:19 UTC
Views: 44
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.