CVE-2026-42271 BerriAI LiteLLM Command Injection Vulnerability
Exploitation active constatée
· catalogue CISA KEVDescription
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before version 1.83.7, two endpoints used to preview an MCP server before saving it — POST /mcp-rest/test/connection and POST /mcp-rest/test/tools/list — accepted a full server configuration in the request body, including the command, args, and env fields used by the stdio transport. When called with a stdio configuration, the endpoints attempted to connect, which spawned the supplied command as a subprocess on the proxy host with the privileges of the proxy process. The endpoints were gated only by a valid proxy API key, with no role check. Any authenticated user — including holders of low-privilege internal-user keys — could therefore run arbitrary commands on the host. This issue has been patched in version 1.83.7.
Produits et versions touchés
| Produit | Versions touchées | Corrigé en |
|---|---|---|
| litellm 1.74 | 1.74.2 → < 1.83.7 | 1.83.7 |
| Red Hat OpenShift AI 2.25 1781826406 | premières → < 1781826406 | 1781826406 |
| Red Hat OpenShift AI 3.3 1782310008 | premières → < 1782310008 | 1782310008 |
| Red Hat OpenShift AI 3.4 1781622627 | premières → < 1781622627 | 1781622627 |
| Exploit Intelligence | Versions non publiées | |
| Red Hat Ansible Automation Platform 2 | Versions non publiées | |
| Red Hat OpenShift AI (RHOAI) | Versions non publiées |
Références
- github.com github.com
- github.com github.com
Chronologie
- Publiée
- Ajoutée au catalogue KEV
- Dernière modification