CVE-2026-105760: medium-severity vulnerability in vllm-project vllm
vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion
Published · Updated
13Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 5.3epss 0.3%
exploitation probability
0.3%top 79% of all CVEs
observed exploitation
nono source reports it
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates an attacker-sized pre-decode frame-index list, allowing a compact request and tiny valid video to consume disproportionate CPU time and memory in the shared media-loading executor. This issue is fixed in version 0.30.0.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
Affected products
vllm-project · vllmRelated CVEs — vllm-project vllm
In the same product, most dangerous first.
CVE-2026-22778CRITICALvLLM leaks a heap address when PIL throws an errorEPSS 11.2%CVE-2026-27893HIGHvLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-outEPSS 1.8%CVE-2025-32444CRITICALvLLM Vulnerable to Remote Code Execution via Mooncake IntegrationEPSS 1.8%CVE-2026-48746CRITICALvLLM: OpenAI auth bypassEPSS 1.2%CVE-2025-47277CRITICALvLLM Allows Remote Code Execution via PyNcclPipe Communication ServiceEPSS 1.0%CVE-2025-62164HIGHVLLM deserialization vulnerability leading to DoS and potential RCEEPSS 0.9%