CVE-2026-80047 Affecting vllm package, versions *


Severity

Recommended
low

Based on default assessment until relevant scores are available.

Threat Intelligence

EPSS
0.1% (1st percentile)

Do your applications use this vulnerable package?

In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.

Test your applications
  • Snyk IDSNYK-MINIMOSLATEST-VLLM-20372600
  • published2 Oct 2026
  • disclosed1 Sept 2026

Introduced: 1 Sep 2026

CVE-2026-80047  (opens in a new tab)

How to fix?

There is no fixed version for Minimos:latest vllm.

NVD Description

Note: Versions mentioned in the description apply only to the upstream vllm package and not the vllm package as distributed by Minimos. See How to fix? for Minimos:latest relevant fixed versions and status.

A vulnerability in Hugging Face Transformers (versions 4.57.0 to 5.16.1) allows remote Python files to be written to local disk without user consent when using GenerativePreTrainedModel.load_custom_generate(). The function fetches and caches a remote module file before performing the required trust_remote_code consent check, inverting the security model enforced by other code-loading paths (such as AutoConfig, AutoModel, and AutoTokenizer). As a result, attacker‑controlled Python code from custom_generate/generate.py is copied into the user’s ~/.cache/huggingface/modules directory even if the user declines the trust prompt. Although execution is correctly gated, the file write is not reversible and can persist across sessions. This can lead to persistent, unauthorized files on disk and stale cache collisions where cached attacker code may later be executed during trusted model loads. The issue stems from an unconditional file write in dynamic_module_utils.py prior to any trust verification.