CVE-2026-42271
LiteLLM: Authenticated command execution via MCP stdio test endpoints
- Published
- May 8, 2026
- Updated
- Jul 15, 2026
- Assigning CNA
- GitHub_M
- Evidence observed
- Jun 8, 2026
Primary CVSS
nvd · CVSS 4.0
CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:XHigh · next 30 days
- Percentile
- 99.7%
- Model date
- Sep 21, 2026
EPSS is a statistical estimate, not a certainty or a measure of impact. Combine it with CVSS, KEV status, exposure and your environment.
CISA Known Exploited
This CVE appears in the CISA Known Exploited Vulnerabilities catalog.
Summary
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.
Sources
2- litellm-command-injection-security-assessmentInformational
Professional vulnerability assessment report for LiteLLM command injection risk, including executive summary, technical impact, remediation, and mitigation strategy.
- CVE-2026-42271-PoCExploit
The code for personally reproducing the corresponding vulnerability
Responsible use
Use vulnerability information only on systems you own or are authorized to test. Kitploit links to public research metadata and does not store exploit code or malicious payloads.