UNKNOWN PyPI
CVE-2026-93436
PYSEC-2026-3996 · CVE-2026-93436
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 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.
References
- WEB https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/push_worker.py#L162-L181
- ADVISORY https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-rejected-requests
- FIX https://github.com/vllm-project/vllm/pull/55677
- PACKAGE https://github.com/vllm-project/vllm
Ready to move
Start Securing
Free, no credit card | First findings in minutes