CVE-2026-94623

7.5 HIGHpublic exploit available

Published 2026-09-21 · Updated 2026-09-21

AI risk analysis

Summary: The flaw allows attackers to trigger an assertion failure in vLLM's NIXL connector by submitting multi-prompt completion requests, leading to service disruption.
Exploitability: Exploitation requires sending specific crafted requests; preconditions include using a version of vLLM prior to 0.29.1 which addresses the issue.
Blast radius: If exploited, it could cause the decode worker to terminate and become unavailable until restarted, impacting service availability.
Prioritized remediation: Update to vLLM version 0.29.1 or later to mitigate the vulnerability.

dosservice-disruptionupdate

Analysis generated locally by qwen2.5:7b-instruct (no data left the box). AI-assisted — verify against primary sources before acting.

NVD 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.

CVSS vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Weaknesses

CWE-617

Public exploit & PoC references

All references

Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.

Related CVEs

Related by shared AI tags and CWE weakness class. Browse the full archive.