~ / search / GHSA-6wvf-77m9-58rm

GHSA-6wvf-77m9-58rm

LiteLLM vulnerable to server-side template injection in the /prompts/test endpoint

Source: GitHub Advisory Database (reviewed) Critical CVE-2026-37004

Packages

EcosystemPackageAffectedFixed in
PyPI litellm < 1.83.7 1.83.7

Details

As written in the advisory (Markdown source, shown as plain text).

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

External links from the advisory. They lead to third-party sites.