Advisory

PYSEC-2026-2297

Also known as: CVE-2026-27893, GHSA-7972-pg2x-xr59

Summary

The record has no summary.

Details

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 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. Version 0.18.0 patches the issue.

Severity

High Basis: CVSS v3 score 8.8, vector CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Dates

Published
2026-03-27 00:16 UTC
Modified
2026-07-13 07:15 UTC

Affected packages and fixes

vllm

PyPI · All systems

Affected

  • introduced 0.10.1, fixed 0.18.0 (ecosystem)

Fixed versions

0.18.0

Fix

  • Fixed version 0.18.0
    pip install --upgrade vllm==0.18.0

Fix 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

View this record on OSV.dev

Source

Source: PyPA Advisory Database · CC BY 4.0

Sources & licences