SEPTEMBER 9, 2026
Live Feed
Back to database
Case File

CVE-2026-50144

HIGH · CVSS 7.1 Public Exploit

Source: NVD + CISA KEV + EPSS · Published 2026-07-15 · Last synced 2026-08-14

CyberRota Analysis

AI-Generated

The ncnn framework is vulnerable to an out-of-bounds heap write due to improper validation of parameter IDs when loading malicious .param model files, potentially leading to memory corruption and arbitrary code execution. This high-severity issue affects all versions prior to the fix in commit 5a0288f255daa6c3294f77109f67718e434ec020. Organizations utilizing ncnn for mobile neural network applications should prioritize patching to mitigate the risk of exploitation.

Public Exploit Signal

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

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

CVE
CVE-2026-50144
Severity
HIGH
CVSS
7.1
EPSS
N/A

Original NVD Description

ncnn is a high-performance neural network inference framework optimized for the mobile platform. In commit e54f7b1f88434e1d844ea0551b880a1cfb079ce1 and earlier, ncnn allows an out-of-bounds heap write in ncnn::ParamDict::load_param() when Net::load_param() loads a malicious .param model file because the parsed parameter id is checked only against id >= NCNN_MAX_PARAM_COUNT, allowing a negative id to index before the params[NCNN_MAX_PARAM_COUNT] array. This vulnerability is fixed by commit 5a0288f255daa6c3294f77109f67718e434ec020.