'Ghostcommit' hides prompt injection in images to fool AI agents, steal secrets

A PNG hiding a prompt injection could steal your repo's secrets, researchers demonstrate. The technique, dubbed 'Ghostcommit, ...

Claude Code Espionage Campaign Exposes a New Enterprise AI Risk

Anthropic’s AI-run espionage report shows why enterprises need stronger governance for AI agents, MCP connectors, and ...
SecurityWeek

AI Coding Tools Tricked Into Hacking Developer Machine via Decades-Old Technique

Several AI coding assistants were tricked into facilitating developer machine hacking via an attack technique that has been ...
Computer Weekly

Insurer Unum aims to deliver benefits of $20m using AI to re-write old Cobol code

Last year, Unum partnered with Amazon Web Services and Pegasystems, which provides a low-code platform to Fortune 500 companies to automate their business processes, in a project to re-engineer Unum’s ...
The Hacker News

AI Coding Agents Found Triggering Endpoint Security Rules Built to Catch Attackers

Sophos says Claude Code, Cursor, and Codex triggered Windows endpoint rules for credential access, LOLBin downloads, and ...