CVE-2026-114055High· 7.5▾ TwilightvLLM from 0.7.3 before 0.31.0 contains an uncontrolled resource consumption vulnerability that allows remote clients to control multimodal processor parameters by supplying per-request mm_processor_kwargs. Attackers can set large image s…
▾ Twilight zone — High severity, or a signal on a lesser flaw
impact 41.3 · likelihood 0.1 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
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. The CVSS score shown above comes from the assigning CNA record, not NVD.
Exploit-prediction probability, daily snapshots since Oct 21.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via CVEORG
0.3%
Last analysed / modified upstream
0.3% → 0.4%
vLLM from 0.7.3 before 0.31.0 contains an uncontrolled resource consumption vulnerability that allows remote clients to control multimodal processor parameters by supplying per-request mm_processor_kwargs. Attackers can set large image size, patch count, crop count, or frame count values in Isaac, InternVL, H2OVL, and other processors to exhaust memory and terminate the shared server.
vllm >= 0.7.3 < 0.31.0Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Affected packages:
vllm >= 0.7.3, < 0.31.0Patched in:
vllm 0.31.0Source: https://osv.dev/vulnerability/GHSA-gx7p-2j49-hfq4
Connected by shared product, vendor, weakness, or advisory.
CVE-2026-69147Medium· 6.5vLLM is an inference and serving engine for large language models
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-2026-114050Medium· 6.5vLLM: Forged multimodal UUID + P0/P1 processor-cache eviction drift: unauthenticated remote crash of the whole vLLM engine
CVE-2026-105758Medium· 5.3vLLM is an inference and serving engine for large language models
CVE-2026-100650Medium· 6.5vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-p…