Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.
An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...
Mozilla’s 0din team showed how a Claude Code malware GitHub repo attack could use a clean-looking repository to open a ...
“Honestly, AI slop [pull requests] are becoming increasingly draining and demoralizing for #Godot maintainers,” Verschelde ...
A new technical paper, Agentic Hardware Design as Repository-Level Code Evolution, was published by researchers at Nvidia ...
Mozilla researchers revealed a new attack that tricks Claude Code into running hidden commands from seemingly harmless GitHub repositories.
GoodData.AI positioned as a Visionary by Gartner® for completeness of vision and ability to execute. SAN FRANCISCO, CA ...
New AI agent enables engineering teams to plan, execute, and manage complex code changes across hundreds or thousands of ...
GitHub secret scanning now extends beyond org-owned repositories: Public Monitoring scans all of GitHub.com in real time, ...
Infosecurity spoke with the researcher who dumped over 30 proof-of-concept exploits without disclosing the vulnerabilities ...
The project will ban substantial AI-generated code contributions. Autonomous AI agents and vibe coding will continue to trigger automatic GitHub bans. All pull requests must continue to be reviewed ...
Malicious apps got into the Arch User Repository - how to protect yourself ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results