INCIDENT MAP

Browse / Unsafe Model Loading and Supply Chain / CVE-2026-22807

vLLM affected by RCE via auto_map dynamic module loading during model initialization

CVE-2026-22807 · 2026-01-21 high

Class
Unsafe Model Loading and Supply Chain (filed by a model that read the advisory)
Technique
Code and command execution
Affected
vllm (PyPI)
Gets past
Safe model loader or scanner
CVSS
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
EPSS
1.0% chance of exploitation in 30 days

How it works, in short

A model repository's auto_map entry makes vLLM import attacker Python during model resolution, even with trust_remote_code disabled. (Our summary, written by a model. The source text is below.)

Details

Summary

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.

---

Impact

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.

---

Affected Versions

All versions where vllm/model_executor/models/registry.py resolves auto_map entries with try_get_class_from_dynamic_module without checking trust_remote_code (at least current main).

---

Details

During model resolution, vLLM unconditionally iterates auto_map entries from the model config and calls try_get_class_from_dynamic_module, which delegates to Transformers’ get_class_from_dynamic_module and executes the module code.

This occurs even when trust_remote_code is false, allowing a malicious model repo to embed code in a referenced module and have it executed during initialization.

Relevant code

---

Fixes

Credits

Reported by bugbunny.ai

References

Source: GitHub Advisory Database, used under CC BY 4.0.