vllm
Affected
- introduced
0.10.1, fixed0.18.0(ecosystem)
Fixed versions
0.18.0
Fix
- Fixed version
0.18.0pip install --upgrade vllm==0.18.0
Advisory
Also known as: CVE-2026-27893, PYSEC-2026-2297
vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out
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):
vllm/model_executor/models/nemotron_vl.py:430 vision_model = AutoModel.from_config(config.vision_config, trust_remote_code=True)
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:
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.
High Basis: The source's own band: HIGH
0.10.1, fixed 0.18.0 (ecosystem)0.18.0
0.18.0pip install --upgrade vllm==0.18.0Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: GitHub Advisory Database (reviewed advisories) · CC BY 4.0