vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out

Summary Two model implementation files hardcode trustremotecode=True when loading sub-components, bypassing the user's explicit --trust-remote-code=False security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code...

GHSA-7972-PG2X-XR59 vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out

Summary Two model implementation files hardcode trustremotecode=True when loading sub-components, bypassing the user's explicit --trust-remote-code=False security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code...

Unsafe Dependency Resolution

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Unsafe Dependency Resolution in the process of loading sub-components with the trustremotecode parameter set to True, regardless of user...

GHSA-3C37-WWVX-H642 vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-12.9, localstack, py3-vllm-cuda-12.4, tritonserver-backend-vllm-cuda-13.0, py3-cbor2...

CVE-2026-26209 vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-12.9, localstack, py3-vllm-cuda-12.4, tritonserver-backend-vllm-cuda-13.0, py3-cbor2...

CVE-2026-22778 vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm-cuda-13.0, tritonserver-backend-vllm-cuda-12.9...

GHSA-GRG2-63FW-F2QR vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm-cuda-13.0, tritonserver-backend-vllm-cuda-12.9...

GHSA-4R2X-XPJR-7CVV vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm-cuda-13.0, tritonserver-backend-vllm-cuda-12.9...

CVE-2026-22773 vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm-cuda-13.0, tritonserver-backend-vllm-cuda-12.9...

CVE-2026-24779 vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm-cuda-13.0, tritonserver-backend-vllm-cuda-12.9...

GHSA-QH4C-XF7M-GXFC vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm-cuda-13.0, tritonserver-backend-vllm-cuda-12.9...

PYSEC-2026-2297

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...

PYSEC-2026-2297

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...

vLLM 安全漏洞

vLLM is an open-source LLM-based inference and service engine that features high throughput and efficient memory usage. Versions of vLLM prior to 0.10.1 to 0.18.0 contained a security vulnerability. This vulnerability stemmed from the hardcoding of trustremotecode=True in two model implementation...

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...

CVE-2026-27893

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...

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...

PT-2026-28373

Name of the Vulnerable Software and Affected Versions vLLM versions 0.10.1 through 0.17.x Description vLLM is an inference and serving engine for large language models LLMs. Starting with version 0.10.1 and continuing through version 0.17.x, two model implementation files hardcode trust remote...

CVE-2026-27893: Protection Mechanism Failure

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...

The vulnerability of the MultiModalHasher class in the library for working with Large Language Models (LLMs) allows a hacker to disclose protected information.

The vulnerability of the MultiModalHasher class in the library for working with Large Language Models LLMs vLLM is related to improper verification of consistency in input data. Exploiting this vulnerability can allow a remote attacker to disclose sensitive information that is protected by this...