Vulnerability 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.
CVSS Score
HIGH
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.10.1, < 0.18.0 |
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011aPatch
- https://github.com/vllm-project/vllm/pull/36192Issue Tracking
- https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59Vendor Advisory
FAQ
What is CVE-2026-27893?
CVE-2026-27893 is a vulnerability with a CVSS score of 8.8 (HIGH). 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 ...
How severe is CVE-2026-27893?
CVE-2026-27893 has been rated HIGH with a CVSS base score of 8.8/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-27893?
Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.