AI Threat Alert
vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the...
Full analysis pending. Showing NVD description excerpt.
Affected Systems
| Package | Ecosystem | Vulnerable Range | Patched |
|---|---|---|---|
| vllm | pip | < 0.9.0 | 0.9.0 |
| vllm | pip | — | No patch |
Severity & Risk
Recommended Action
Patch available
Update vllm to version 0.9.0
Compliance Impact
Compliance analysis pending. Sign in for full compliance mapping when available.
Technical Details
NVD Description
vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has been patched in version 0.9.0.
Weaknesses (CWE)
CVSS Vector
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:N References
- github.com/advisories/GHSA-4qjh-9fv9-r85r
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-53.yaml
- github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f
- github.com/vllm-project/vllm/pull/17045
- github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r
- nvd.nist.gov/vuln/detail/CVE-2025-46570
- github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f Patch
- github.com/vllm-project/vllm/pull/17045 Issue Vendor
- github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r Vendor