Nixpkgs security tracker

Login with GitHub

Suggestion detail

Untriaged
Permalink CVE-2026-73558
5.3 MEDIUM
  • CVSS version (CVSS): 3.1
  • Attack Vector (AV): Network (N)
  • Attack Complexity (AC): High (H)
  • Privileges Required (PR): None (N)
  • User Interaction (UI): Required (R)
  • Scope (S): Unchanged (U)
  • Confidentiality (C): High (H)
  • Integrity (I): None (N)
  • Availability (A): None (N)
  • Modified Attack Vector (MAV): Network (N)
  • Modified Attack Complexity (MAC): High (H)
  • Modified Privileges Required (MPR): None (N)
  • Modified User Interaction (MUI): Required (R)
  • Modified Confidentiality (MC): High (H)
  • Modified Scope (MS): Unchanged (U)
  • Modified Integrity (MI): None (N)
  • Modified Availability (MA): None (N)
created 1 week, 3 days ago Activity log
  • Created suggestion 1 week, 3 days ago
vLLM: Cross-User Data Leak Vulnerability

vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or complete copy of another user's inference result. This issue is fixed in version 0.27.0.

Affected products

vllm
  • ==< 0.27.0

Matching in nixpkgs

pkgs.vllm

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

Package maintainers