Skip to content
Advisories.
vLLMGHSA-2pc9-4j83-qjmr

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

High8.8CVE-2026-22807 · Published Jan 21, 2026 · updated Sep 10, 2026

# 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 - `vllm/model_executor/models/registr...

GitHub advisory

Affected versions

PackageAffectedFixed in
vllm
PyPI
>= 0.10.1, < 0.14.00.14.0
Details and references

# 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 - `vllm/model_executor/models/registry.py:856` , auto_map resolution - `vllm/transformers_utils/dynamic_module.py:13` , delegates to `get_class_from_dynamic_module`, which executes code --- # Fixes * https://github.com/vllm-project/vllm/pull/32194 # Credits Reported by **bugbunny.ai**

CVSS 3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Severity from
GitHub (reviewed advisory)
Weakness
CWE-94
Also known as
CVE-2026-22807, PYSEC-2026-2010

More vLLM advisories

All vLLM
Advisory
vLLM has SSRF Protection Bypass
Medium5.4Mar 9
vLLM has RCE In Video Processing
Critical9.8Feb 2
vLLM vulnerable to Server-Side Request Forgery (SSRF) through MediaConnector
High7.1Jan 28
vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions
Medium6.5Jan 13
vLLM introduced enhanced protection for CVE-2025-62164
High8.8Jan 8
vLLM vulnerable to remote code execution via transformers_utils/get_config
High7.1Dec 2, 2025

Critical advisories by email

Wednesdays: the week’s critical and high advisories in the AI and data stack, with the fixed versions. Only in weeks that have some.

Double opt-in. Unsubscribe any time.