Nixpkgs Security Tracker

Login with GitHub
⚠️ You are using a production deployment that is still only suitable for demo purposes. Any work done in this might be wiped later without notice.

Suggestion detail

Untriaged
(browse all)
Permalink CVE-2026-22778
created 5 hours ago
vLLM leaks a heap address when PIL throws an error

vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.

Affected products

vllm
  • ==>= 0.8.3, < 0.14.1

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