Cross-user token data leakage in async scheduling + Pipeline Parallelism
GHSA-v97p-wpxp-px84 · published 2026-11-09
- Severity
- Medium
- CVSS score
- 4.8
- Chance of exploitation (EPSS)
- No CVE
- Fixed in
- 0.21.0
This constitutes a cross-user data leak in multi-tenant inference deployments. In environments where users submit sensitive or private prompts (e.g., personal information, proprietary business data, medical or legal content), fragments of one user's context can influence or appear in another user's output.
Upgrade vllm to 0.21.0 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.
For deployments on affected versions, either of these settings mitigates the issue. Launching vLLM with --no-async-scheduling Setting pipeline_parallel_size=1 (disabling pipeline parallelism) A fix for this was introduced in https://github.com/vllm-project/vllm/pull/41133.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| vllm | PyPI | >= 0.16.0, < 0.21.0 | 0.21.0 |
- 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: OpenAI auth bypassvllm
- 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
The impact, patch and workaround text comes from the advisory, shortened (published by vLLM). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.