6.5
CVE-2026-105756
- EPSS 0.31%
- Veröffentlicht 05.10.2026 22:49:59
- Zuletzt bearbeitet 08.10.2026 01:28:23
- Erkennungen
LoginvLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cache_salt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the LMCache-MP connector, a salt that contains a forbidden character or exceeds the permitted length can raise an uncaught ValueError during scheduler cache lookup, causing EngineCore to terminate and denying service to all concurrent users. This issue is fixed in version 0.30.0.
| Typ | Quelle | Score | Percentile |
|---|---|---|---|
| EPSS | FIRST.org | 0.31% | 0.22 |
| Quelle | Base Score | Exploit Score | Impact Score | Vector String |
|---|---|---|---|---|
| security-advisories@github.com | 6.5 | 2.8 | 3.6 |
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
|
CWE-20 Improper Input Validation
The product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly.
CWE-248 Uncaught Exception
An exception is thrown from a function, but it is not caught.
Für Zugriff zu Vulnerability Intelligence ist ein VulnDex Zugang erforderlich.
https://github.com/vllm-project/vllm/releases/tag/v0.30.0
https://github.com/vllm-project/vllm/security/advisories/GHSA-2823-qmq8-rwvj
https://github.com/vllm-project/vllm/pull/51444
https://github.com/vllm-project/vllm/commit/e962733e08d10f7ca65dac4df99e116460b8b174