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

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

After publicly touting pull request limits as a way to cut maintainer noise, GitHub is taking the same idea further with a new setting that lets repository admins restrict issue creation to ...

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 ...

Overview Windsurf and Amazon Q Developer, two familiar AI coding brands, will have each moved into different product areas by ...

The Godot Foundation have announced a crackdown on genAI code, including mandatory disclosures, following a wave of ...

Karpathy CLAUDE.md ten rules: a document attributed to Andrej Karpathy began circulating Friday, adding six agent self-check ...

Three levels of indirection, all with seemingly innocuous steps, will catch a bot off-guard.

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

LayerX found that BioShocking could trick AI browsers into leaking credentials by disguising malicious prompts as game rules.

Godot has updated its contribution policy and "take[n] steps" to reduce "demoralizing" AI contributions. In a frank statement posted on its website, the Godot Foundation talked candidly about the ...

Lovable makes extensive use of AI to help anyone create, and publish web apps with ease.