CVE-2026-37004 LiteLLM vulnerable to server-side template injection in the /prompts/test endpoint
Unauthenticated attackers can execute arbitrary OS commands via Server-Side Template Injection in the LiteLLM library's prompt testing endpoint.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-37004?
CVE-2026-37004 is a critical code injection vulnerability in n/a, published on 27 Aug 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official 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.
Weakness: CWE-1336
Which versions are affected by CVE-2026-37004?
3 open source packages ship an affected version, including litellm.
| Package | Affected | Fixed in |
|---|---|---|
litellm PyPI | All versions | 1.83.7 |
litellm PyPI | All versions | 1.83.7 |
litellm PyPI | All versions | 1.83.7 |
How do I fix CVE-2026-37004?
Upgrade litellm to 1.83.7 or later.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-37004 being exploited?
There is no known exploitation of CVE-2026-37004 in the wild and no public exploit code.
Sources
Also known as ECHO-a062-523f-e726, GHSA-6wvf-77m9-58rm, MINI-79gg-82x6-83mm, MINI-7mmg-h5fw-q8pf, MINI-9j6v-jprr-rjq9, MINI-qwhw-vf95-r25r and 3 more.