Description
vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded list[str] or list[list[int]], prompt_to_seq() in vllm/renderers/inputs/preprocess.py and OnlineRenderer.preprocess_completion() in vllm/renderers/online_renderer.py expand every element, and vllm/entrypoints/openai/completion/serving.py creates one engine generator and response slot per prompt, allowing an authenticated API client to exhaust CPU, memory, async scheduling capacity, engine request slots, and response buffering with one request. This issue is fixed in version 0.26.0.
Affected products
vllm: vllm
References5
- github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3… ExploitVendor Advisory
- github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3… ExploitVendor Advisory
- github.com/vllm-project/vllm/commit/675f4295cdfe0d870471c2b51bf… Patch
- github.com/vllm-project/vllm/pull/47845 Issue TrackingPatch
- github.com/vllm-project/vllm/releases/tag/v0.26.0 Release Notes
Metrics
- CVSS 3.1
-
6.5
MEDIUM
Score source: CNA
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H - EPSS — exploit probability
- 1% percentile: 48 · as of 12 November 2026
- CWE
- CWE-400
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.