| ID |
CVE-2025-62164
|
| Sažetak |
vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash (denial-of-service) and potentially remote code execution (RCE), exists in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using torch.load() without sufficient validation. Due to a change introduced in PyTorch 2.8.0, sparse tensor integrity checks are disabled by default. As a result, maliciously crafted tensors can bypass internal bounds checks and trigger an out-of-bounds memory write during the call to to_dense(). This memory corruption can crash vLLM and potentially lead to code execution on the server hosting vLLM. This issue has been patched in version 0.11.1. |
| Reference |
|
| CVSS |
| Base: | 8.8 |
| Impact: | 5.9 |
| Exploitability: | 2.8 |
|
| Pristup |
| Vektor | Složenost | Autentikacija |
| NETWORK |
LOW |
LOW |
|
| Impact |
| Povjerljivost | Cjelovitost | Dostupnost |
| HIGH |
HIGH |
HIGH |
|
| CVSS vektor |
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H |
| Zadnje važnije ažuriranje |
04-12-2025 - 17:14 |
| Objavljeno |
21-11-2025 - 02:15 |
