AUGUST 4, 2026
Live Feed
Back to database
Case File

CVE-2025-62164

HIGH · CVSS 8.8 EPSS 0.93% Public Exploit

Source: NVD + CISA KEV + EPSS (historical backfill) · Published 2025-11-21 · Last synced 2026-08-04

CyberRota Analysis

This is a high severity vulnerability with a CVSS score of 8.8. Public exploit code or proof-of-concept references have been detected in its references. It may be remotely exploitable. It may lead to a denial-of-service condition.

Public Exploit Signal

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

Detected Signals
remote code execution code execution

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

CVE
CVE-2025-62164
Severity
HIGH
CVSS
8.8
EPSS
0.93%

Original NVD Description

vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash (denial-of-service) and potentially remote code execution (RCE), exists in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using torch.load() without sufficient validation. Due to a change introduced in PyTorch 2.8.0, sparse tensor integrity checks are disabled by default. As a result, maliciously crafted tensors can bypass internal bounds checks and trigger an out-of-bounds memory write during the call to to_dense(). This memory corruption can crash vLLM and potentially lead to code execution on the server hosting vLLM. This issue has been patched in version 0.11.1.

Related CVEs

Other vulnerabilities affecting the same vendor(s)