vLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode disaggregated deployments. Remote attackers can submit requests with max_tokens=0 to exhaust decode-worker memory without bound until the worker restarts.
https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-rejected-requests
Published: 2026-09-17
Updated: 2026-09-22
Base Score: 7.8
Vector: CVSS2#AV:N/AC:L/Au:N/C:N/I:N/A:C
Severity: High
Base Score: 7.5
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Severity: High
Base Score: 8.7
Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
Severity: High
EPSS: 0.00538