Vulnerability in Vllm-project Vllm
CVE-2026-27893
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 u…
EPSS: 0.000 (14.7th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 8.8 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H.
Affected products
- Vllm-project Vllm — versions >= 0.10.1, < 0.18.0
Weakness classification (CWE)
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59 (x_refsource_CONFIRM)
- https://github.com/vllm-project/vllm/pull/36192 (x_refsource_MISC)
- https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72 (x_refsource_MISC)
Frequently asked questions
- What is CVE-2026-27893?
- CVE-2026-27893 is a high-severity vulnerability in Vllm-project Vllm, classified under Protection Mechanism Failure. CVSS score: 8.8/10. Published 2026-03-26.
- How severe is CVE-2026-27893?
- High severity. CVSS v3 base score is 8.8 out of 10.