vLLM through 0.29.0 Denial of Service via Incomplete NIXL KV Transfer Metadata

Advisories

vLLM through 0.29.0 Denial of Service via Incomplete NIXL KV Transfer Metadata

severity: high
date: 9/21/2026
Affecting: vllm <= 0.29.0
CVE: CVE-2026-94622
CWE: CWE-248 Uncaught Exception
CVSS: 8.7
CVSS V4 Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
References: Pull Request #54807
https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/metadata.py#L294-L312
https://github.com/vllm-project/vllm
Credit: Mingkai Yu, Jiapeng Li, Jiajia Liu
Description: 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.

Ready to get Started?

Explore VulnCheck, a next-generation Cyber Threat Intelligence platform, which provides exploit and vulnerability intelligence to help you prioritize and remediate vulnerabilities that matter.

Vulnerability Prioritization
Prioritize vulnerabilities that matter based on the threat landscape and defer vulnerabilities that don't.
Early Warning System
Real-time alerting of changes in the vulnerability landscape so that you can take action before the attacks start.

Schedule a Demo