Nixpkgs security tracker

Login with GitHub

Details of issue NIXPKGS-2026-1556

NIXPKGS-2026-1556
published on
Permalink CVE-2026-44222
6.5 MEDIUM
  • CVSS version (CVSS): 3.1
  • Attack Vector (AV): Network (N)
  • Attack Complexity (AC): Low (L)
  • Privileges Required (PR): Low (L)
  • User Interaction (UI): None (N)
  • Scope (S): Unchanged (U)
  • Confidentiality (C): None (N)
  • Integrity (I): None (N)
  • Availability (A): High (H)
  • Modified Attack Vector (MAV): Network (N)
  • Modified Attack Complexity (MAC): Low (L)
  • Modified Privileges Required (MPR): Low (L)
  • Modified User Interaction (MUI): None (N)
  • Modified Confidentiality (MC): None (N)
  • Modified Scope (MS): Unchanged (U)
  • Modified Integrity (MI): None (N)
  • Modified Availability (MA): High (H)
updated 4 hours ago by @LeSuisse Activity log
  • Created suggestion
  • @LeSuisse accepted
  • @LeSuisse published on GitHub
vLLM: Remote DoS via Special-Token Placeholders

vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder sequences supplied without matching data cause vLLM to index into empty grids during input-position computation, raising an unhandled IndexError and terminating the worker or degrading availability. Multimodal paths that rely on image_grid_thw/video_grid_thw are affected. This vulnerability is fixed in 0.20.0.

Affected products

vllm
  • ==>= 0.6.1, < 0.20.0

Matching in nixpkgs

pkgs.vllm

High-throughput and memory-efficient inference and serving engine for LLMs

Package maintainers