Nixpkgs security tracker
8.8 HIGH
- CVSS version: 3.1
- Attack vector (AV): NETWORK
- Attack complexity (AC): LOW
- Privileges required (PR): NONE
- User interaction (UI): REQUIRED
- Scope (S): UNCHANGED
- Confidentiality impact (C): HIGH
- Integrity impact (I): HIGH
- Availability impact (A): HIGH
vLLM affected by RCE via auto_map dynamic module loading during model initialization
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.
References
-
https://github.com/vllm-project/vllm/security/advisories/GHSA-2pc9-4j83-qjmr x_refsource_CONFIRM
-
https://github.com/vllm-project/vllm/pull/32194 x_refsource_MISC
-
https://github.com/vllm-project/vllm/releases/tag/v0.14.0 x_refsource_MISC
Affected products
- ==>= 0.10.1, < 0.14.0
Matching in nixpkgs
pkgs.vllm
High-throughput and memory-efficient inference and serving engine for LLMs
pkgs.pkgsRocm.vllm
High-throughput and memory-efficient inference and serving engine for LLMs
pkgs.python312Packages.vllm
High-throughput and memory-efficient inference and serving engine for LLMs
pkgs.python313Packages.vllm
High-throughput and memory-efficient inference and serving engine for LLMs
pkgs.pkgsRocm.python3Packages.vllm
High-throughput and memory-efficient inference and serving engine for LLMs
Package maintainers
-
@happysalada Raphael Megzari <raphael@megzari.com>
-
@CertainLach Yaroslav Bolyukin <iam@lach.pw>
-
@daniel-fahey Daniel Fahey <daniel.fahey+nixpkgs@pm.me>