Pierluigi Paganini
September 29, 2026
UK AISI finds GPT-6 Astra launches unsanctioned supply-chain attacks in simulations far more than earlier OpenAI models, even when told not to. The UK’s AI Security Institute tested GPT-6 Astra before its public release, and the results, published September 28, aren’t subtle. When given a routine cybersecurity evaluation, the model went off script and attacked […]
Pierluigi Paganini
September 28, 2026
Infostealers are exposing corporate AI accounts, sessions and API keys, giving attackers access to sensitive data, compute and connected systems. SOCRadar analyzed stealer log data from the last 90 days and found 482 companies with exposed AI accounts and credentials. Of those, 295 appeared in active logs during that period, suggesting the exposure is recent […]
Pierluigi Paganini
September 28, 2026
Microsoft details Storm-3168, the JADEPUFFER-linked actor that used stolen service principals to delete Azure storage in minutes and harvest keys. Microsoft just published the first detailed look at what JADEPUFFER does inside Azure. Sysdig first spotted the group’s activity in July 2026 and called it the first documented agentic ransomware operation. Microsoft tracks the same […]
Pierluigi Paganini
September 27, 2026
Security Affairs AI-CYBERSECURITY newsletter includes a collection of the best articles and research on AI in the international landscape Artificial intelligence is rapidly changing cybersecurity, reshaping both the techniques used by attackers and the tools available to defenders. AI agents can automate tasks, analyze large amounts of data, discover vulnerabilities and accelerate offensive operations. At […]
Pierluigi Paganini
September 26, 2026
OpenAI is investigating AI agents that accessed US gov websites without authorization, including an attempted Education Department hack. OpenAI disclosed on Friday that its AI agents had interacted with US government websites in ways nobody planned or authorized, as part of what the company is calling an ongoing review of unexpected model behavior. The affected […]
Pierluigi Paganini
September 25, 2026
CARBONATO exploits exposed Docker daemons, installs an AI agent, steals API keys and spreads across networks with autonomous command execution. CARBONATO is a Docker-based botnet that has been active since at least October 2024. ThreatDown discovered the operation after finding an unauthenticated container registry exposed to the internet. The registry contained the attackers’ entire toolchain […]
Pierluigi Paganini
September 23, 2026
Microsoft, Coinbase and law enforcement took down EvilTokens, a phishing kit that compromised 12,000 inboxes through device-code phishing and AI. EvilTokens showed up in February 2026 and moved fast. Within months it had compromised more than 12,000 inboxes across over 10,000 organizations. Microsoft says the EvilTokens platform, operated by Storm-2992, is a phishing-as-a-service kit sold […]
Pierluigi Paganini
September 21, 2026
AI agents are becoming the new attack surface, exposed to poisoned skills, prompt injection, jailbreaks and attacks through connected tools. I read the AI security research published in a single month, February 2026, and when you put it all together, it’s not a list of curiosities. It’s a field guide to a new attack surface. […]
Pierluigi Paganini
September 20, 2026
An AI-generated intelligence report falsely identified weapons on a Chinese ship, nearly triggering a US military operation during the Iran war. According to CNN, four sources familiar with the episode say an intelligence report circulated through the military claiming a Chinese vessel in the Middle East was carrying components for a nuclear weapons program. The […]
Pierluigi Paganini
September 17, 2026
OpenAI launches a formal framework to disclose model misalignment, publishing six reports on models that lied, faked data, or bypassed rules. Most companies don’t publish a document explaining how their product misbehaves. OpenAI just did. On September 16, it released a formal framework for tracking, investigating, and disclosing cases of model misalignment, paired with six […]
