Vulnerability in Vllm
CVE-2026-93436
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.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 7.5 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H.
EPSS exploit prediction
EPSS: 0.008 (55.1th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 55th percentile — 55.1% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.008 · newest: 0.008 · change: 0.000
Affected products
Weakness classification (CWE)
References
- github.com/vllm-project/vllm/pull/55677 (issue-tracking, Patch, patch, Issue Tracking)
- github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_conne… (Product, technical-description)
- github.com/vllm-project/vllm (Product, product)
- www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-rejected… (Third Party Advisory, third-party-advisory)
Frequently asked questions
- What is CVE-2026-93436?
- CVE-2026-93436 is a high-severity vulnerability in Vllm, classified under Missing Release of Memory after Effective Lifetime. CVSS score: 7.5/10. Published 2026-09-17.
- How severe is CVE-2026-93436?
- High severity. CVSS v3 base score is 7.5 out of 10.