CVE-2026-93592

Faiblesse

vLLM versions before 0.28.0 fail to validate the lower bound of token IDs in the /v1/embeddings and /pooling endpoints, allowing unauthenticated attackers to crash the engine by submitting negative token IDs. A single request with a negative token ID triggers a CUDA device-side assertion that poisons the GPU context, causing all subsequent requests to fail until the process restarts.

Références

• https://github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm-8vpf
• https://www.vulncheck.com/advisories/vllm-before-0.28.0-denial-of-service-via-negative-token-id
• https://github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm-8vpf