Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.
The release includes an embedded MCP server that exposes Spring project analytics to AI coding assistants, along with first-class support for Spring AI and automated property refactoring.
I wrote a prompt when I should've written a condition ...
The terminal's not so scary anymore ...
Add Decrypt as your preferred source to see more of our stories on Google. Microsoft researchers found that Anthropic's Claude Code GitHub Action could be manipulated through prompt injection attacks.