SOC status:Duty analyst on shift

UK Cyber Defence
VulnerabilityAwaiting Analysis

CVE-2026-73559

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…

MEDIUM 6.5EPSS 0.47%

Does this matter?

Lower severity and a low EPSS score (0.47%). Track it; it rarely justifies an emergency change on its own.

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.

CVSS 3.1
6.5 MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
EPSS
0.47% probability · 39th percentile
CISA KEV
Not listed
Weakness
CWE-400
Source
security-advisories@github.com

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.