vLLM: OpenAI auth bypass
CVE-2026-48746 · GHSA-94f4-hr76-p5j6 · published 2026-06-16 · updated 2026-09-01
- Severity
- Critical
- CVSS score
- 9.1
- Chance of exploitation (EPSS)
- 1.2%
- Fixed in
- 0.22.0
- Exploitation Public proof of concept
- Automatable Yes
- Technical impact Partial
- CISA SSVC
Instances of vllm that use an API Key for the OpenAI API and expose the API to attackers. Instances behind an RFC-conforming web server (such as nginx) are not affected.
Upgrade vllm to 0.22.0 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| vllm | PyPI | >= 0.3.0, < 0.22.0 | 0.22.0 |
- CriticalLiteLLM has SQL Injection in Proxy API key verificationlitellmExploited
- Criticaln8n Vulnerable to Remote Code Execution via Expression Injectionn8n, n8nExploited
- HighLiteLLM has a sandbox escape in custom-code guardraillitellmExploited
- HighLangflow affected by Remote Code Execution via validate_code() exec()langflowExploited
- CriticalJupyter MCP Server: Browser DNS rebinding can hijack the Jupyter backend through management routesjupyter-mcp-server
- Criticalmem0ai Databricks vector store vulnerable to SQL injectionmem0ai
- CriticalvLLM has RCE In Video Processingvllm
- CriticalvLLM Allows Remote Code Execution via PyNcclPipe Communication Servicevllm
- CriticalvLLM Vulnerable to Remote Code Execution via Mooncake Integrationvllm
- CriticalCVE-2025-24357 Malicious model remote code execution fix bypass with PyTorch < 2.6.0vllm
- CriticalvLLM Deserialization of Untrusted Data vulnerabilityvllm
- CriticalvLLM allows Remote Code Execution by Pickle Deserialization via AsyncEngineRPCServer() RPC server entrypointsvllm
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.