WS-2026-0157

vllm 0.10.2 - 0.24.0: the Nemotron-VL processor modules set Image.MAXIMAGEPIXELS = None at import, disabling Pillow's decompression-bomb guard process-wide so a crafted image can exhaust worker memory GHSA-mm38-5g96-7j6x...

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,...

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,...

CVE-2026-4944

The provided documents describe a vulnerability in vllm-project/vllm version 0.14.1 where trust_remote_code is hardcoded to True in nemotron_vl.py and kimi_k25.py, bypassing user-specified --trust-remote-code=False and enabling remote code execution via malicious HuggingFace model repositories. T...

PT-2025-48580

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.11.1 Description vLLM is an inference and serving engine for large language models LLMs. A critical issue exists in the Nemotron Nano VL Config class where remote code execution can occur. When vLLM loads a model...