Lucene search
+L

3 matches found

BDU FSTEC
BDU FSTEC
•added 2026/08/03 12:00 a.m.•12 views

The vulnerability of the vllm-metal inference backend component of the Docker Desktop Docker Model Runner plugin allows a attacker to execute arbitrary code.

The vulnerability of the vllm-metal inference backend component of the Docker Desktop Docker Model Runner plugin is related to the inclusion of functions from an unverified controlled area. Exploiting this vulnerability could allow a attacker to execute arbitrary code...

8.6CVSS5.9AI score0.00184EPSS
SaveExploits1References2Affected Software1
EUVD
EUVD
•added 2026/05/22 7:24 p.m.•23 views

EUVD-2026-31493

The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trustremotecode=True when loading model tokenizers, and runs without sandboxing. This causes transformers.AutoTokenizer.frompretrained to import and execute arbitrary Python files included in any model pulled fr...

8.8CVSS6.5AI score0.00184EPSS
SaveExploits1References1
Positive Technologies
Positive Technologies
•added 2026/05/22 12:00 a.m.•39 views

PT-2026-42830

Name of the Vulnerable Software and Affected Versions Docker Model Runner on macOS affected versions not specified Description The vllm-metal inference backend unconditionally sets trust remote code=True when loading model tokenizers and operates without sandboxing. This allows the...

8.8CVSS6.4AI score0.00184EPSS
SaveExploits1References7
Rows per page
Query Builder