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

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 ...

Researchers found Cordyceps CI/CD flaws affecting 300+ repositories, enabling code execution, credential theft, and supply ...

Multiple weaponized proof-of-concept (PoC) exploits on GitHub delivered a Python-based remote access trojan (RAT) called ChocoPoC that can execute commands and steal sensitive data. However, ChocoPoC ...

VS Code can use LLM models other than GitHub Copilot’s built-in providers for AI-assisted development, including local and ...

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

Mozilla 0DIN’s Claude Code demo shows how clean GitHub repos can expose AI coding agents to prompt injection, reverse shells, and credential risk.

Cordyceps, a systemic class of exploitable CI/CD vulnerabilities, allows unauthenticated attackers to hijack developer ...

Hackers injected malware into 73 Microsoft GitHub repos on June 5, 2026. The attack targeted AI coding tools like Claude Code and VS Code. Read what happened.

"If we improve the code and we can all benefit from it, it's good for everyone," says Fenris's Ben Hunter, as he talks ...

Azure Functions shipped a serverless agents runtime in public preview at Build 2026. Agents are defined in .agent.md markdown ...