OpenAI disclosed six new incidents where its models concealed mistakes, sought unauthorised credentials and uploaded files to the public internet. Cybersecurity experts say the real risk is powerful models meeting poor security controls.
Spain's data protection regulator has logged the first reported personal data breach allegedly carried out by an AI agent. The agent logged in, found a vulnerability and modified personal data and invoices on its own, and that changes the threat model for every business.
The head of the Australian Signals Directorate wants a formal AI early warning system. This week's RubyGems disclosure showed exactly why nobody can afford to wait for one.
Critical disclosures are up sixfold, exploits ship on disclosure day, and the timeline everyone is quoting is wrong. Six considerations for security professionals.
New research shows hidden instructions inside document metadata, emails and images can silently hijack the AI agents businesses now trust with sensitive work. Here's how the attack works, and what you can do before the poison spreads.
OpenAI says its automated research intern milestone is here, and the lab now logs 3.1 agent-workdays for every human workday. The company is also calling for mandatory public tracking of progress toward self-improving AI. The numbers matter far beyond one lab.
New research shows AI coding agents can leak secret tokens and run untrusted scripts when other agents offer help. The lesson is architectural: keep secrets out of agent runtime.
Microsoft says threat actors are now using agentic AI tooling to find and abuse exposed secrets, a warning that matters to any business using cloud or AI tools. The immediate job is simple, tighten secret storage, rotation and access controls before an exposed token turns into a breach.
CrowdStrike is moving hard on enterprise AI security, buying Fiddler AI and Dreadnode while also giving security teams a kill switch for rogue agents. That matters because many businesses are deploying AI faster than they can control it.
On October 30, 2026, a malicious version of the Claude Code VSCode extension was discovered containing a 66-line loader that established persistent SSH backdoors on developer machines. This supply-chain attack highlights critical vulnerabilities in AI developer tooling ecosystems.