Nixpkgs security tracker

Untriaged

Permalink CVE-2026-73559

6.5 MEDIUM

CVSS version (CVSS): 3.1
Attack Vector (AV): Network (N)
Attack Complexity (AC): Low (L)
Privileges Required (PR): Low (L)
User Interaction (UI): None (N)
Scope (S): Unchanged (U)
Confidentiality (C): None (N)
Integrity (I): None (N)
Availability (A): High (H)
Modified Attack Vector (MAV): Network (N)
Modified Attack Complexity (MAC): Low (L)
Modified Privileges Required (MPR): Low (L)
Modified User Interaction (MUI): None (N)
Modified Confidentiality (MC): None (N)
Modified Scope (MS): Unchanged (U)
Modified Integrity (MI): None (N)
Modified Availability (MA): High (H)

created 1 week, 3 days ago Activity log

Created suggestion 1 week, 3 days ago

vLLM: Completion prompt lists fan out into unbounded engine requests

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.