AUGUST 4, 2026
Live Feed
Back to database
Case File

CVE-2025-46570

LOW · CVSS 2.6 EPSS 0.26% Public Exploit

Source: NVD + CISA KEV + EPSS (historical backfill) · Published 2025-05-29 · Last synced 2026-08-04

CyberRota Analysis

This is a low severity vulnerability with a CVSS score of 2.6. Public exploit code or proof-of-concept references have been detected in its references.

Public Exploit Signal

A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.

Detected Signals
exploit

Note: these links are listed for security research and verification purposes only.

CVE
CVE-2025-46570
Severity
LOW
CVSS
2.6
EPSS
0.26%

Original NVD Description

vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has been patched in version 0.9.0.

Related CVEs

Other vulnerabilities affecting the same vendor(s)