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 ...
SecurityWeek

Researchers Demo New Claude Code Attack Using Harmless-Looking Repositories to Hijack Developer Machines

Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.
Windows Report

Mozilla Warns Clean GitHub Repositories Can Trick Claude Code Into Running Malware

Mozilla researchers revealed a new attack that tricks Claude Code into running hidden commands from seemingly harmless GitHub ...
International Business Times

Malicious GitHub Repositories Could Trick AI Coding Agents Into Running Hidden Malware, Researchers Warn

Researchers warn malicious GitHub repositories can trick AI coding agents into running hidden malware through trusted setup steps, risking developer systems and credentials. Google - Gemini A newly ...
IEEE

FACT: Fast and Active Coordinate Initialization for Vision-Based Drone Swarms

Abstract: Coordinate initialization is the first step in accomplishing collaborative tasks within robot swarms, determining the quality of tasks. However, fast and robust coordinate initialization in ...
IEEE

Spectral Structure-Aware Initialization and Probability-Consistent Self-Training for Cross-Scene Hyperspectral Image Classification

Abstract: Cross-scene classification of hyperspectral images (HSIs) aims to classify target domain (TD) data using only labeled source domain (SD) data and unlabeled TD data during training. However, ...
GitHub

RampNet: A Two-Stage Pipeline for Bootstrapping Curb Ramp Detection in Streetscape Images from Open Government Metadata

RampNet is a two-stage pipeline that addresses the scarcity of curb ramp detection datasets by using government location data to automatically generate over 210,000 annotated Google Street View ...
GitHub

luckeciano/chemistry-lab-env

A Gymnasium environment implementing the Chemical Lab GridWorld — a partially observable grid task with portals, trunks, and goal uncertainty — plus four baselines: Bayesian Oracle, Q-Learning, LLM ...