vLLM from 0.28.0 before 0.30.0 contains a reachable assertion vulnerability in GPUModelRunner._init_xdrope_positions that allows remote attackers to crash the engine by submitting embeddings-only requests. Attackers can send a /v1/completions request containing only prompt_embeds to XD-RoPE models with --enable-prompt-embeds, terminating the EngineCore and API server for all clients.
CVSS Details
- CVSS 4.0 Base Score: 8.2 (HIGH)
- CVSS 4.0 Vector: (CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X)
- CVSS 3.1 Base Score: 5.9
- CVSS 3.1 Vector: (CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H)
Prioritize with Active Threat Intelligence
With curated Threat Intelligence, you can see which vulnerabilities truly put you at risk, prioritize what matters most, and act before attackers do.
Explore Intelligence Hub