vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out
Published 27 Mar 2026 · Updated 10 Sept 2026
Is your project on an affected vllm?
Look after several Python apps? Indie watches up to 15 repos, private ones too, for $5 a month. See Indie
Affected package
- Affected
- >=0.10.1 <0.18.0
- Fixed in
- 0.18.0
pip install 'vllm>=0.18.0'Details
Summary
Two model implementation files hardcode trust_remote_code=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 trust.
### Details
Affected files (latest main branch):
1. vllm/model_executor/models/nemotron_vl.py:430
vision_model = AutoModel.from_config(config.vision_config, trust_remote_code=True)
2. vllm/model_executor/models/kimi_k25.py:177
cached_get_image_processor(self.ctx.model_config.model, trust_remote_code=True)
Both pass a hardcoded trust_remote_code=True to HuggingFace API calls, overriding the user's global --trust-remote-code=False setting.
Relation to prior CVEs:
- CVE-2025-66448 fixed auto_map resolution in vllm/transformers_utils/config.py (config loading path)
- CVE-2026-22807 fixed broader auto_map at startup
- Both fixes are present in the current code. These hardcoded instances in model files survived both patches — different code paths.
Impact
Remote code execution. An attacker can craft a malicious model repository that executes arbitrary Python code when loaded by vLLM, even when the user has explicitly set --trust-remote-code=False. This undermines the security guarantee that trust_remote_code=False is intended to provide.
Remediation: Replace hardcoded trust_remote_code=True with self.config.model_config.trust_remote_code in both files. Raise a clear error if the model component requires remote code but the user hasn't opted in.
Is GHSA-7972-pg2x-xr59 in any of your client repos?
Checking one package by hand is fine. Checking it across forty client projects is not. NPMscan reads the lockfiles in every GitHub repo you pick, finds each project with an affected vllm, and gives you the command that fixes it.
More advisories for vllm
- LowCVE-2026-115917vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server · 28 Oct 2026
- MediumCVE-2026-115913vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine · 28 Oct 2026
- MediumCVE-2026-115914vLLM DeepSeek-OCR image processing vulnerable to denial of service · 28 Oct 2026
- HighCVE-2026-115915vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE · 28 Oct 2026
- HighCVE-2026-115912vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled · 28 Oct 2026
- MediumCVE-2026-115916vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS) · 28 Oct 2026
References
- Linkgithub.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59
- Advisorynvd.nist.gov/vuln/detail/CVE-2026-27893
- Linkgithub.com/vllm-project/vllm/pull/36192
- Linkgithub.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72
- Linksecurity.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-27893.json
- Packagegithub.com/vllm-project/vllm
- Linkgithub.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2297.yaml
- Linkbugzilla.redhat.com/show_bug.cgi?id=2452055
- Linkaccess.redhat.com/security/cve/CVE-2026-27893
- Linkaccess.redhat.com/errata/RHSA-2026:8748
- Linkaccess.redhat.com/errata/RHSA-2026:8747
- Linkaccess.redhat.com/errata/RHSA-2026:8746
- Linkaccess.redhat.com/errata/RHSA-2026:37275
- Linkaccess.redhat.com/errata/RHSA-2026:24977
- Linkaccess.redhat.com/errata/RHSA-2026:19725
- Linkaccess.redhat.com/errata/RHSA-2026:19724
- Linkaccess.redhat.com/errata/RHSA-2026:19712
- Linkaccess.redhat.com/errata/RHSA-2026:10141
- Linkaccess.redhat.com/errata/RHSA-2026:10140
Advisory data from OSV.dev (opens OSV.dev in a new tab), refreshed daily.