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.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| BerriAI | litellm | >= 1.80.5, < 1.83.7 | — |
Fixed in Linux distributions
Distributions backport fixes, so the version that fixes this vulnerability differs per release — upgrade to at least the version shown. From the distributions' security trackers and advisories.
Wolfi
| Release | Package | Fixed in | Advisory |
|---|---|---|---|
| Wolfi rolling | airflow-3 | 3.2.2-r7 | — |
Public exploits
Exploit or proof-of-concept code for this vulnerability is publicly available, which lowers the bar for attackers. Treat it as a reason to patch sooner.
GitHub 1 repository
-
Astianjy/CVE-2026-42203 ★ 0 · May 15, 2026
Sources: PoC-in-GitHub, Metasploit Framework, Exploit-DB — updated daily. Only links are listed; no exploit code is hosted here.
Affected packages
| Ecosystem | Package | Affected | Fixed | Record |
|---|---|---|---|---|
| PyPI | litellm | >= 1.80.5, < 1.83.7 | 1.83.7 | GHSA-xqmj-j6mv-4862 |
Advisories 1
- WID-SEC-2026-1422 LiteLLM: Schwachstelle ermöglicht Codeausführung und Offenlegung von Informationen BSI CERT-Bund (WID) · May 7, 2026