Description
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.
Metrics
CVSS 3.1 7.5/10
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:HWeakness enumeration
Affected software
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | < 0.28.0 |
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm-8vpfExploit, Mitigation, Patch, Vendor Advisory
- https://www.vulncheck.com/advisories/vllm-before-0.28.0-denial-of-service-via-negative-token-idThird Party Advisory
- https://github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm-8vpfExploit, Mitigation, Patch, Vendor Advisory
Timeline
- Published
- Sep 18, 2026
- Last modified
- Sep 28, 2026
- NVD status
- Analyzed