MSRXCVE-2026-42271
CVE-2026-42271
LiteLLM: Authenticated command execution via MCP stdio test endpoints
Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.
CVSS 4.0 · CNA
chance of exploitation in the next 30 days (EPSS; in the top 1% of all CVEs)
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.
Scores
Affected packages and fixed versions
| Package | Ecosystem | Fixed in |
|---|---|---|
| litellm | PyPI | 1.83.7 |
Affected products
- BerriAI litellm: >= 1.74.2, < 1.83.7
Also known as: GHSA-v4p8-mg3p-g94g, PYSEC-2026-2599
2 references (advisories, patches, write-ups)
- https://github.com/BerriAI/litellm/security/advisories/GHSA-v4p8-mg3p-g94g · x_refsource_CONFIRM
- https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable · x_refsource_MISC
Sources: CVE.org, OSV.dev, FIRST EPSS. Missing ones did not answer or have no record yet.