vLLM: Completion prompt lists fan out into unbounded engine requests
CVE-2026-73559 · GHSA-87x5-vmc3-756j · published 2026-08-13
- Severity
- Medium
- CVSS score
- 6.5
- Chance of exploitation (EPSS)
- 0.58%
- Fixed in
- 0.26.0
- Exploitation Public proof of concept
- Automatable No
- Technical impact Partial
- CISA SSVC
An authenticated API client can make one /v1/completions request consume CPU, memory, async task scheduling, engine request slots, and response buffering proportional to an attacker-chosen outer prompt list. This can starve or disrupt other tenants sharing the same vLLM server. The report does not claim unauthenticated access, confidentiality impact, integrity impact, code execution, or impact where /v1/completions is not reachable by untrusted or semi-trusted clients.
Upgrade vllm to 0.26.0 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.
Reject oversized prompt lists before renderer preprocessing. Add an outer prompt-count limit to CompletionRequest.prompt when the prompt is list[str] or list[list[int]], and consider making the limit configurable in the same style as the batch-chat and sampling-list bounds. The check should run before OnlineRenderer.preprocess_completion() expands the prompt sequence, so oversized requests do not allocate parsed prompt lists, async render/tokenization tasks, engine generators, or response result slots. Regression coverage should include a scalar prompt, a bounded prompt list, an oversized list[str], and an oversized list[list[int]].
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| vllm | PyPI | >= 0.19.0, < 0.26.0 | 0.26.0 |
- HightsParticles: Unbounded HTTP Request Body Buffering in @tsparticles/mcp-server Leads to Remote DoS@tsparticles/mcp-server
- HighMCP TypeScript SDK: HTTP server transports and handlers did not limit request body size or JSON-RPC batch length@modelcontextprotocol/hono, @modelcontextprotocol/node, @modelcontextprotocol/sdk, @modelcontextprotocol/server
- HighMCP TypeScript SDK: One HTTP request within the default size limit could exhaust server memory during validation@modelcontextprotocol/sdk, @modelcontextprotocol/server
- HighHTTP server transports and OAuth endpoints read request bodies with no size limitmcp, mcp
- HighLMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loadinglmdeploy
- HighRMCP: Unauthenticated permanent session-table leak in rmcp Streamable HTTP server transport leads to remote denial-of-servicermcp
- 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 (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.