Live › vulnerability › CVE-2026-118613
Go to dashboardUltralytics' torch_load function deserializes user-supplied data without validation, so a crafted file can execute code. An attacker runs code as the current user once a victim opens a malicious file or visits a malicious page.
Summary written from the sources below. Check the originals before acting.
First seen by InfraStack 2026-10-28 17:34 UTC. All times on this page are UTC.
Teams that run Ultralytics and load model or data files supplied from outside, such as user uploads or downloaded weights, are exposed. Systems that only load their own vetted model files are less exposed; the sources do not say more.
No product ranges from the sources yet.
pip show ultralytics and compare it to the fixed release in the advisory, which the sources do not nametorch_load or loading of untrusted model files: unknownultralytics package to a version newer than the affected one: unknown (the sources do not give the fixed version)Each row is the first time that source carried this signal. The analyst’s rows are its own findings.
Ultralytics torch_load Deserialization of Untrusted Data Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Ultralytics. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file.
The specific flaw exists within the torch_load function. The issue results from the lack of proper validation of user-supplied data, which can result in deserialization of untrusted data. An attacker can leverage this vulnerability to execute code in the context of the current user. Was ZDI-CAN-29652.
This page as .md · .json · in your agent: get_signal("CVE-2026-118613")
NVD data is provided by NIST and is public domain. Posts quoted belong to their authors.