CVE-2026-69147Medium· 6.5▾ TwilightPoC availablevLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set media_io_kwargs.video.video_backend to pynvvideocodec, and MediaConnector.fetch_video forwards …
▾ Twilight zone — High severity, or a signal on a lesser flaw
impact 35.8 · likelihood 0.1 · exploitation 12
A public proof-of-concept already exists for this vulnerability — see Exploit availability below.
Stakeholder-Specific Vulnerability Categorization from CISA's ADP record at CVE.org: whether exploitation is observed, whether an attack can be automated, and how much of the system is at stake.
Exploit-prediction probability, daily snapshots since Sep 19.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
Exploit / PoC code exists
0.5%
Last analysed / modified upstream
0.5% → 0.6%
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set media_io_kwargs.video.video_backend to pynvvideocodec, and MediaConnector.fetch_video forwards that choice to VideoMediaIO even when startup configuration selected a software decoder. The engine's _reserve_mm_ipc_gpu_memory logic budgets decoder memory only from static configuration, so the request-selected VIDEO_LOADER_REGISTRY backend can create a CUDA context, decoder surfaces, and decoded-frame allocations that were not removed from the engine's KV-cache budget. An attacker able to submit video requests to a video-capable GPU deployment with PyNvVideoCodec installed can exhaust shared GPU memory, causing request failures, worker crashes, or denial of service. The first release containing the fix is version 0.28.0.
vllm < 0.28.0Upgrade past the affected range:
vllm 0.28.0Affected packages:
vllm < 0.28.0Patched in:
vllm 0.28.0Source: https://github.com/advisories/GHSA-8pw2-6jv3-mj5j
Field changes observed since this record was first indexed.
Connected by shared product, vendor, weakness, or advisory.
CVE-2026-71486Medium· 4.3vLLM is an inference and serving engine for large language models
CVE-2026-73559Medium· 6.5vLLM is an inference and serving engine for large language models
CVE-2026-105760Medium· 5.3vLLM is an inference and serving engine for large language models
CVE-2026-73556Medium· 5.3vLLM is an inference and serving engine for large language models
CVE-2026-114055High· 7.5vLLM 0.7.3 before 0.31.0 DoS via Unvalidated mm_processor_kwargs
CVE-2026-105758Medium· 5.3vLLM is an inference and serving engine for large language models