Lucene search
K

6 matches found

NVD
NVD
added 2026/05/28 7:16 p.m.6 views

CVE-2026-4944

vllm-project/vllm version 0.14.1 contains a vulnerability where the trustremotecode=True parameter is hardcoded in two model implementation files vllm/modelexecutor/models/nemotronvl.py and vllm/modelexecutor/models/kimik25.py. This bypasses the user's explicit --trust-remote-code=False setting,...

8.8CVSS0.00097EPSS
Exploits0References1
Vulnrichment
Vulnrichment
added 2026/05/28 6:4 p.m.5 views

CVE-2026-4944 Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control

vllm-project/vllm version 0.14.1 contains a vulnerability where the trustremotecode=True parameter is hardcoded in two model implementation files vllm/modelexecutor/models/nemotronvl.py and vllm/modelexecutor/models/kimik25.py. This bypasses the user's explicit --trust-remote-code=False setting,...

8.8CVSS7.9AI score0.00097EPSS
Exploits0References1
EUVD
EUVD
added 2026/05/28 6:4 p.m.9 views

EUVD-2026-32979

vllm-project/vllm version 0.14.1 contains a vulnerability where the trustremotecode=True parameter is hardcoded in two model implementation files vllm/modelexecutor/models/nemotronvl.py and vllm/modelexecutor/models/kimik25.py. This bypasses the user's explicit --trust-remote-code=False setting,...

8.8CVSS7.9AI score0.00097EPSS
Exploits0References1
Positive Technologies
Positive Technologies
added 2026/05/28 12:0 a.m.3 views

PT-2026-44487

vllm-project/vllm version 0.14.1 contains a vulnerability where the trust remote code=True parameter is hardcoded in two model implementation files vllm/model executor/models/nemotron vl.py and vllm/model executor/models/kimi k25.py. This bypasses the user's explicit --trust-remote-code=False...

8.8CVSS7.9AI score0.00097EPSS
Exploits0References2
OSV
OSV
added 2026/03/26 11:56 p.m.1 views

CVE-2026-27893 vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out

vLLM is an inference and serving engine for large language models LLMs. Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode trustremotecode=True when loading sub-components, bypassing the user's explicit --trust-remote-code=False security opt-out. This...

8.8CVSS6.5AI score0.00046EPSS
Exploits0References5
Cvelist
Cvelist
added 2026/03/26 11:56 p.m.22 views

CVE-2026-27893 vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out

vLLM is an inference and serving engine for large language models LLMs. Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode trustremotecode=True when loading sub-components, bypassing the user's explicit --trust-remote-code=False security opt-out. This...

8.8CVSS0.00046EPSS
Exploits0References3
Rows per page
Query Builder