CVE-2026-93436
HIGHCVSS 7.5Description
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.
Timeline
Published:September 17th, 2026 11:18 PM
Last modified:September 28th, 2026 6:37 PM
CVSS Scoring
CVSS v3: 7.5 (HIGH)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Affected Software
From NVD CPE configuration data
Vendors
vllm
Products
vllm
Weaknesses (CWE)
References & Reports
Advisories, patches, and third-party reports
- https://github.com/vllm-project/vllmProduct
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/push_worker.py#L162-L181Product
- https://github.com/vllm-project/vllm/pull/55677Issue Tracking
- https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-rejected-requestsThird Party Advisory
Source: NIST NVD · Data may lag official sources by up to one minute