Clean GitHub repo tricks AI coding agents into running malware

An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...
techtimes

Open-Source Coding Model Ornith-1.0 Writes Its Own Training Scaffold in Reinforcement Learning

DeepReinforce today released Ornith-1.0, a family of open-source coding models built around a mechanism most RL-trained agents avoid: the model itself writes the training harness that guides its own ...
WeLiveSecurity

Award-winning news, views, and insight from the ESET security community

Your business may be small, but its attack surface is anything but. Readiness is the first step to resilience. Gamaredon in 2025: Leveraging tunnels, workers, dead drops, and new alliances ESET ...
Dark Reading

Vulnerabilities & Threats

Vulnerabilities & Threats Insider Threats Сloud Security Amazon Q VS Extension Flaw Leads to Cloud Credential Theft Adversaries could plant a malicious repository that can execute arbitrary code and ...