High severity · published Sep 17, 2026
CVE-2026-93436
vLLM through 0.29.0 Memory Exhaustion via Rejected Requests
7.5
CVSS
0.8%
EPSS
No
On KEV
Description
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 vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
None
Integrity
None
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.8% · higher than 55% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
VL
vllm · vllm-project
through 0.29.0 · source: vendor, NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-93436
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-93436
Product
https://github.com/vllm-project/vllm
Product
https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/push_worker.py#L162-L181
Issue Tracking
https://github.com/vllm-project/vllm/pull/55677
Third Party Advisory
https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-rejected-requests
More from vllm
9.8
CVE-2026-25960
SSRF Protection Bypass in vLLM
9.8
CVE-2026-22778
vLLM leaks a heap address when PIL throws an error
9.8
CVE-2024-9053
vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer() RPC server entrypoints
9.1
CVE-2026-48746
vLLM: OpenAI auth bypass
8.8
CVE-2026-54232
vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile