CVE-2026-27893 | BDVDB-2026-323161 Detail

Description#

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.

Impact#

Weaknesses#

References#

Exploit#

History#

1. Version 12026-03-26Record published in the CVE List.
2. Version 22026-07-27Most recent update recorded in the CVE List.