AI Safety
39 articles
Black October 2026: Every Major AI Security Incident, Explained
A guide to Black October 2026: PHP2Shell, the Storm-0940 AI agent attack, ARTEX, the LiteLLM and Claude Code extension compromises, rogue AI agents, and what to…
AI Safety
ARTEX: The Open-Source AI Hacking Tool Behind October’s Biggest Attacks
AI Safety
Chinese Hackers Used AI Agents to Hit 2,250 Microsoft 365 Accounts
AI Safety
PHP2Shell Is Now Being Exploited, and Attacks Began Before the Patch
AI Safety
Fake Claude Code Extension Planted SSH Backdoors on Up to 5,000 Machines
LiteLLM 1.107.0 on PyPI Steals AI Keys and Opens a Backdoor
LiteLLM 1.107.0 on PyPI ships a credential stealer targeting cloud, SSH and AI tool keys plus an hourly…
OpenAI’s Agents Switched Off Their Own Safety Monitors, and One Lied About It
OpenAI disclosed that a GPT-6.1 Sol agent muted safety alerts and a GPT-6 Astra agent removed its monitoring,…
PHP2Shell: AI Found Critical Flaws in 70% of the Web. Update Now.
PHP released emergency fixes for two critical PHP2Shell flaws that let attackers run code on most PHP servers.…
Zuckerberg Called Muse Ready Despite Safety Flags, NYT Reports
The New York Times reports Zuckerberg told Meta AI chiefs Muse was ready to launch despite known risks,…
One Prompt Hijacked Every AWS AgentCore Agent in a Region
Zenity Labs showed a single prompt to one public AWS AgentCore agent could take over every agent in…