News & Sicurezza

A vulnerability was found in Moore Threads MTT S80 Driver Package 340.150. The affected element is the function sub_140006F0C in the library mtdispkm64.sys of the component IOCTL Handler. The manipulation results in improper privilege management. Attacking locally is a requirement. The vendor was contacted early about this disclosure but did not respond in any way.

CVE ID :CVE-2026-94425 Published : Sept. 21, 2026, 11:16 p.m. | 7 hours, 10 minutes ago Description :A vulnerability was found in Moore Threads MTT S80 Driver Package 340.150. The affected element is the function sub_140006F0C in the library mtdispkm64.sys of the component IOCTL Handler. The manipulation results in improper privilege management. Attacking locally is a requirement. The vendor was contacted early about this disclosure but did not respond in any way. Severity: 9.3 | CRITICAL Visit the link for more details, such as CVSS details, affected products, timeline, and more...

vLLM Mooncake connector through 0.29.0 fails to properly manage GPU KV cache block ownership when concurrent child requests share a single transfer ID in prefill/decode disaggregated deployments. Attackers can trigger GPU memory exhaustion by submitting completion requests with multiple prompts, causing orphaned KV cache blocks to accumulate until process restart and eventually preventing legitimate requests from executing.

vLLM through 0.29.0 fails to validate the tp_size parameter in kv_transfer_params on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tp_size values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel OOM-kill of the decode worker process.

vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is configured with TieringOffloadingSpec and a peer-to-peer secondary tier. Attackers can supply arbitrary remote host and port values in kv_transfer_params to create unreachable peer sessions that retain ZeroMQ sockets until the context quota is exhausted, causing an uncaught ZMQError that crashes EngineCore and stops all inference.

vLLM through 0.29.0 contains a denial of service vulnerability in the NIXL connector's prefix caching implementation that fails to properly validate block counts across multi-prompt completion requests in prefill/decode disaggregated deployments. Attackers can trigger an assertion failure in NixlBaseConnectorWorker._apply_prefix_caching by submitting completion requests with multiple prompts of varying lengths, causing the decode worker to terminate and become unavailable until restarted.

CVE ID :CVE-2026-94626 Published : Sept. 21, 2026, 10:17 p.m. | 8 hours, 10 minutes ago Description :vLLM through 0.29.0 fails to validate the tp_size parameter in kv_transfer_params on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tp_size values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel OOM-kill of the decode worker process. Severity: 8.7 | HIGH Visit the link for more details, such as CVSS details, affected products, timeline, and more...

CVE ID :CVE-2026-94627 Published : Sept. 21, 2026, 10:17 p.m. | 8 hours, 10 minutes ago Description :vLLM Mooncake connector through 0.29.0 fails to properly manage GPU KV cache block ownership when concurrent child requests share a single transfer ID in prefill/decode disaggregated deployments. Attackers can trigger GPU memory exhaustion by submitting completion requests with multiple prompts, causing orphaned KV cache blocks to accumulate until process restart and eventually preventing legitimate requests from executing. Severity: 8.7 | HIGH Visit the link for more details, such as CVSS details, affected products, timeline, and more...

CVE ID :CVE-2026-94623 Published : Sept. 21, 2026, 10:17 p.m. | 8 hours, 10 minutes ago Description :vLLM through 0.29.0 contains a denial of service vulnerability in the NIXL connector's prefix caching implementation that fails to properly validate block counts across multi-prompt completion requests in prefill/decode disaggregated deployments. Attackers can trigger an assertion failure in NixlBaseConnectorWorker._apply_prefix_caching by submitting completion requests with multiple prompts of varying lengths, causing the decode worker to terminate and become unavailable until restarted. Severity: 8.7 | HIGH Visit the link for more details, such as CVSS details, affected products, timeline, and more...

CVE ID :CVE-2026-94625 Published : Sept. 21, 2026, 10:17 p.m. | 8 hours, 10 minutes ago Description :vLLM through 0.29.0 contains a resource exhaustion vulnerability in MooncakeConnector where rejected prefill requests create ownerless transfer placeholders that are never reclaimed. Attackers can send rejected requests to exhaust sender task pools, causing valid requests to be delayed by up to 480 seconds while health checks continue returning success. Severity: 6.9 | MEDIUM Visit the link for more details, such as CVSS details, affected products, timeline, and more...

CVE ID :CVE-2026-94624 Published : Sept. 21, 2026, 10:17 p.m. | 8 hours, 10 minutes ago Description :vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is configured with TieringOffloadingSpec and a peer-to-peer secondary tier. Attackers can supply arbitrary remote host and port values in kv_transfer_params to create unreachable peer sessions that retain ZeroMQ sockets until the context quota is exhausted, causing an uncaught ZMQError that crashes EngineCore and stops all inference. Severity: 8.7 | HIGH Visit the link for more details, such as CVSS details, affected products, timeline, and more...

vLLM versions through 0.29.0 contain a denial of service vulnerability in the NIXL connector's metadata handling for prefill/decode disaggregated deployments. Attackers can send requests with incomplete kv_transfer_params dictionary entries to trigger an uncaught KeyError in EngineCore scheduling, causing the decode engine to terminate and making all routed requests fail until manual restart.