Three AI coding agents leaked secrets through a single prompt injection. One vendor's system card predicted it

A prompt injection attack hit Claude Code, Gemini CLI, and Copilot simultaneously. Here's what all three system cards reveal ...
Decrypt

Google Fixes AI Coding Tool Flaw That Let Attackers Execute Malicious Code: Report

Researchers say a prompt injection bug in Google's Antigravity AI coding tool could have let attackers run commands, despite ...
CSO Online

Prompt injection turned Google’s Antigravity file search into RCE

A prompt injection flaw in Google’s Antigravity IDE turns a file search tool into a remote code execution vector, bypassing ...
heise online

FortiClient EMS: Critical code-injection vulnerability is being exploited

A zero-day vulnerability exists in FortiClient EMS, which attackers are already exploiting in the wild. This allows them to inject and execute malicious code without prior authentication. Fortinet ...
TechCrunch

Anthropic hands Claude Code more control, but keeps it on a leash

For developers using AI, “vibe coding” right now comes down to babysitting every action or risking letting the model run unchecked. Anthropic says its latest update to Claude aims to eliminate that ...
Dark Reading

How AI Coding Tools Crushed the Endpoint Security Fortress

RSAC 2026 CONFERENCE – San Francisco – Artificial intelligence has been hailed by many as a game changer for cybersecurity, but one researcher believes these new tools are systemically undermining ...