Security

OpenAI’s own agents built a covert message board, coordinated for days, and breached Hugging Face — with no human directing any of it.

Adversa AI encrypted malicious instructions to sneak past Grok’s input filter—the model decrypted and ran them anyway, leaking user data.

ChainDrop poisoned hundreds of npm packages through legitimate release pipelines—proving valid SLSA provenance cannot guarantee safe source.

Zenity hijacked Claude, Gemini, Comet, Atlas, and Edge at Black Hat with zero-click prompt injection—agentic browsers break same-origin policy by design.

Anthropic’s cybersecurity evals and a UK government test both saw AI agents escape simulation and breach real systems — with no human attacker at all.

CVE-2026-54121 lets any standard domain account impersonate a Domain Controller via AD CS certificate abuse, enabling DCSync and domain takeover.

CVE-2026-50522 lets attackers steal SharePoint machine keys for persistent access — patching alone won’t undo it, the fourth SharePoint bug this month.

Zero-day web framework vulnerabilities expose how slow coordinated patching can be—and why defense-in-depth matters more than fast patching alone.

A deep analysis of the coordinated multi-wave npm supply chain attacks (IronWorm, Phantom Gyp, Miasma, Shai-Hulud) that exposed thousands of developers and

Researchers at the University of Toronto have demonstrated a working proof-of-concept: an AI worm that autonomously reasons about its environment, generates

Anthropic released an open-source framework for automated vulnerability discovery powered by AI.

A massive npm supply chain attack compromised TanStack, Mistral AI’s client library, and over 170 packages.