Veille CVE
CVE-2026-93592
7.5 ÉlevéeDescription
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.
Produits concernés
Scores CVSS
| Version | Score | Source | Vecteur |
|---|---|---|---|
| 4.0 | 8.7 Élevée | disclosure@vulncheck.com | 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
| 3.1 | 7.5 Élevée | disclosure@vulncheck.com | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H |
Faiblesses (CWE)
Références
- https://github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm-8vpf ExploitMitigationPatchVendor Advisory
- https://www.vulncheck.com/advisories/vllm-before-0.28.0-denial-of-service-via-negative-token-id Third Party Advisory
- https://github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm-8vpf ExploitMitigationPatchVendor Advisory