Zafiyetler / CVE-2026-22807

kritik

CVE-2026-22807

vLLM: vLLM: Arbitrary code execution via untrusted model loading

Yayın Değişiklik CWE 94
En geç 24 Eki 2026, 07:11 UTC tarihinden beri Trivy database'indeO derlemeden önce ne zaman girdiği kayıtlı değil.

Kaynağa göre önem derecesi

NVD9.8CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
GHSA8.8CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Red Hat8.8CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Trivy'nin kendi etiketi CRITICAL. Kritik diyenler: NVD. Daha düşük diyenler: GHSA (yüksek), Red Hat (yüksek).

Açıklama

vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.

Etkilenen paketler ve düzeltilmiş sürümler

KaynakPaketDüzeltildiği sürüm
chainguardpy3-vllm-cuda-12.4, tritonserver-backend-vllm-cuda-12.9, tritonserver-backend-vllm-cuda-13.00.14.0-r0 ve 2 tane daha
pip::GitHub Security Advisory pipvllm0.14.0
2 kaynaktaki 4 kaydın hepsini göster
KaynakPaketDüzeltildiği sürüm
chainguardpy3-vllm-cuda-12.40.14.0-r0
chainguardtritonserver-backend-vllm-cuda-12.925.9.0_git20260318-r0
chainguardtritonserver-backend-vllm-cuda-13.025.11-r2
pip::GitHub Security Advisory pipvllm0.14.0

Referanslar

23 referansın hepsi

Vulnerability data compiled from the Trivy vulnerability database (trivy-db, Aqua Security, Apache License 2.0), which aggregates third-party advisories. CVE records are published by The MITRE Corporation under the CVE Terms of Use; CVE is a trademark of MITRE. This product uses data from the NVD API but is not endorsed or certified by the NVD. Severity, titles and advisory data from the GitHub Advisory Database (CC BY 4.0), Red Hat security data (CC BY 4.0) and the other sources linked on each entry. Entries may be summarised or re-formatted; the linked original is the authoritative record.