Description
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process. The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user could reach it. Depending on how the proxy is deployed, this could expose secrets in the process environment (such as provider API keys or database credentials) and allow commands to be run on the host. This issue has been patched in version 1.83.7.
Metrics
CVSS 3.1 8.8/10
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:HWeakness enumeration
Affected software
| Vendor | Product | Versions |
|---|---|---|
| BerriAI | litellm | >= 1.80.5, < 1.83.7 |
| Red Hat | Exploit Intelligence | — |
| Red Hat | Red Hat Ansible Automation Platform 2 | — |
| Red Hat | Red Hat OpenShift AI (RHOAI) | — |
References
- https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stableProduct, Release Notes
- https://github.com/BerriAI/litellm/security/advisories/GHSA-xqmj-j6mv-4862Mitigation, Patch, Vendor Advisory
- https://access.redhat.com/security/cve/CVE-2026-42203
- https://bugzilla.redhat.com/show_bug.cgi?id=2467917
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-42203.json
Timeline
- Published
- May 8, 2026
- Last modified
- Jul 15, 2026
- NVD status
- Modified