Описание
Diffusers is the a library for pretrained diffusion models. Prior to 0.38.0, a trust_remote_code bypass in DiffusionPipeline.from_pretrained allows arbitrary remote code execution despite the user passing trust_remote_code=False (or omitting it, which is the default). The vulnerability has three variants, all sharing the same root cause — the trust_remote_code gate was implemented inside DiffusionPipeline.download() rather than at the actual dynamic-module load site, so any code path that bypassed or short-circuited download() also bypassed the security check. DiffusionPipeline.from_pretrained('repoA', custom_pipeline='attacker/repoB', trust_remote_code=False) — the gate evaluated against repoA's file list rather than repoB's, so repoB's pipeline.py was loaded and executed. DiffusionPipeline.from_pretrained('/local/snapshot', custom_pipeline='attacker/repoB', trust_remote_code=False) — the local-path branch never invoked download(), so the gate was never reached and remote code from repoB executed. DiffusionPipeline.from_pretrained('/local/snapshot', trust_remote_code=False) where the snapshot contains custom component files (e.g. unet/my_unet_model.py) referenced from model_index.json — same root cause; the local path skipped download() and custom component code executed. This vulnerability is fixed in 0.38.0.
A flaw was found in Diffusers, a library for pretrained diffusion models. A remote attacker could exploit a bypass in the trust_remote_code mechanism within the DiffusionPipeline.from_pretrained function. This vulnerability allows for arbitrary remote code execution, even when the user explicitly sets trust_remote_code=False or omits it. The issue stems from the security check being incorrectly placed, allowing malicious code to be loaded and executed by bypassing the intended security gate.
Отчет
This is an Important vulnerability in Diffusers, a library used in Red Hat AI/ML offerings, that allows arbitrary remote code execution. The trust_remote_code security mechanism in DiffusionPipeline.from_pretrained can be bypassed, enabling the loading and execution of malicious code despite explicit security settings. This misplacement of the security check increases the risk in environments where users load models from external or untrusted repositories.
Меры по смягчению последствий
Use DiffusionPipeline.from_pretrained() only with model paths, custom pipelines, and local snapshots from fully trusted and audited sources. Avoid setting custom_pipeline= to a Hub repository that differs from the primary model path unless its pipeline.py has been manually reviewed. When loading a local snapshot, check for unexpected *.py files at the snapshot root and under component subdirectories (unet/, scheduler/, etc.) before calling from_pretrained. The only complete fix is upgrading to diffusers 0.38.0.
Затронутые пакеты
| Платформа | Пакет | Состояние | Рекомендация | Релиз |
|---|---|---|---|---|
| Red Hat AI Inference Server | rhaiis/vllm-cpu-rhel9 | Will not fix | ||
| Red Hat AI Inference Server | rhaiis/vllm-cuda-rhel9 | Not affected | ||
| Red Hat AI Inference Server | rhaiis/vllm-rocm-rhel9 | Not affected | ||
| Red Hat AI Inference Server | rhaiis/vllm-tpu-rhel9 | Will not fix | ||
| Red Hat AI Inference Server | rhaii/vllm-cpu-rhel9 | Affected | ||
| Red Hat AI Inference Server | rhaii/vllm-cuda-rhel9 | Affected | ||
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-aws-cuda-rhel9 | Affected | ||
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-azure-cuda-rhel9 | Affected | ||
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-cuda-rhel9 | Affected | ||
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-gcp-cuda-rhel9 | Affected |
Показывать по
Дополнительная информация
Статус:
EPSS
8.8 High
CVSS3
Связанные уязвимости
Diffusers is the a library for pretrained diffusion models. Prior to 0.38.0, a trust_remote_code bypass in DiffusionPipeline.from_pretrained allows arbitrary remote code execution despite the user passing trust_remote_code=False (or omitting it, which is the default). The vulnerability has three variants, all sharing the same root cause — the trust_remote_code gate was implemented inside DiffusionPipeline.download() rather than at the actual dynamic-module load site, so any code path that bypassed or short-circuited download() also bypassed the security check. DiffusionPipeline.from_pretrained('repoA', custom_pipeline='attacker/repoB', trust_remote_code=False) — the gate evaluated against repoA's file list rather than repoB's, so repoB's pipeline.py was loaded and executed. DiffusionPipeline.from_pretrained('/local/snapshot', custom_pipeline='attacker/repoB', trust_remote_code=False) — the local-path branch never invoked download(), so the gate was never reached and remote code
Diffusers has a `trust_remote_code` bypass via `custom_pipeline` and local custom components
EPSS
8.8 High
CVSS3