CVE-2026-93436
vLLM through 0.29.0 Memory Exhaustion via Rejected Requests
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.
No summary for this CVE yet.
CVSS Vector Breakdown
Exploitability
AV:NAttack VectorNetwork
AC:LAttack ComplexityLow
PR:NPrivileges RequiredNone
UI:NUser InteractionNone
Scope
S:UScopeUnchanged
Impact
C:NConfidentialityNone
I:NIntegrityNone
A:HAvailabilityHigh
Weaknesses
Affected Products
vllm-project
oss-projectaka vllm, vllm-project/vllm
Exploitability
No known exploits, KEV entries, or remediation guidance available for this vulnerability yet.
References
https://github.com/vllm-project/vllm
github.com
https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/push_worker.py#L162-L181
github.com
https://github.com/vllm-project/vllm/pull/55677
github.com
and 1 more references View all →
Unlock Complete Vulnerability Intelligence
Get the full picture for CVE-2026-93436 and every CVE in our database. Create a free account — no credit card required.
Create Free AccountPlain-language analysis
Impact assessment and exploitation scenario in plain English
Attack graph visualization
Interactive attack path and kill chain mapping
Exploit details & PoC links
ExploitDB, Metasploit, GitHub PoCs with direct links
Nuclei scanner templates
Ready-to-use vulnerability scanner templates
Full remediation guide
Patch instructions, workarounds, and compliance impact
Interactive AI chat
Ask questions about this vulnerability in natural language
Related vulnerabilities
Semantically similar CVEs and attack patterns
REST API & MCP access
Integrate vulnerability data into your workflows