BerriAI · LiteLLM
CVE-2026-42271
LiteLLM: Authenticated command execution via MCP stdio test endpoints
What it is
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.
CISA: BerriAI LiteLLM contains a command injection vulnerability that could allow any authenticated user, including holders of low-privilege internal-user keys, to run arbitrary commands on the host.
What to do
Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.
Deadline for US federal agencies: June 22, 2026
More exploited flaws from BerriAI
| Added | Vulnerability | Product | Severity | Attack chance |
|---|---|---|---|---|
| Sep 2, 2026 | Improper Authentication | LiteLLM | High 8.8 | 0.8% |
| May 8, 2026 | SQL Injection | LiteLLM | Critical 9.3 | 89% |
Sources: Known Exploited Vulnerabilities (CISA, public domain), CVE records (cve.org) and EPSS (FIRST). The chance of attacks is the EPSS estimate that someone will try to exploit the flaw in the next 30 days.