CVE-2026-93436
highpriority · track · 30EPSS 0.008 · 55 %ileUSEPSS · scored 2026-10-27
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.
cvss
Technical severity, 0–10. One row per scoring source.
base score 0–10 · higher = more severe · hover a vector to decode⚠ sources disagree · medium–high · 6.6–8.7
ssvc
A stakeholder decision — act, attend, or track — from exploitation and impact.
weaknesses
The CWE weakness classes this flaw belongs to.
affected products (2)
Products and version ranges known to be affected.
advisories (1)
Vendor and ecosystem advisories describing this.
- PYSEC-2026-39962026-09-17vendor · osvUS
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.
sources
Which sources assert this record, and when.
references (4) nvd
External citations — patches, advisories, analysis.
- 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 TrackingPatch
- https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-rejected-requestsThird Party Advisory
Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.
Free scan