CVE-2026-94623
PYSEC-2026-4005 · CVE-2026-94623
Published · Modified
AI SAST
Find this class of vulnerability in your own code
Corgea's AI-native static analysis detects vulnerabilities like this one across your repositories, ranks them by exploitability, and returns review-ready fixes.
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.
References
- WEB https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/base_worker.py#L2642-L2646
- ADVISORY https://www.vulncheck.com/advisories/vllm-through-0.29.0-denial-of-service-via-nixl-multi-prompt-assertion-failure
- FIX https://github.com/vllm-project/vllm/pull/51505
- PACKAGE https://github.com/vllm-project/vllm
Ready to move
Start Securing
Free, no credit card | First findings in minutes