CVE-2026-27893
vLLM is an inference and serving engine for large language models …
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.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Limit access until thenIf you cannot update at once, take the system off the internet or restrict who can reach it.
References
- github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72
- github.com/vllm-project/vllm/pull/36192
- github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59
- nvd.nist.gov/vuln/detail/CVE-2026-27893
- github.com/advisories/GHSA-7972-pg2x-xr59
- access.redhat.com/errata/RHSA-2026:10140
- access.redhat.com/errata/RHSA-2026:10141
- access.redhat.com/errata/RHSA-2026:19712
- nvd.nist.gov/vuln/detail/CVE-2026-27893
- cve.org/CVERecord?id=CVE-2026-27893
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.