Pierluigi Paganini
August 10, 2026
OpenAI paused work involving Astra after tests showed cybersecurity abilities that could approach its Critical risk threshold under the company’s framework. OpenAI disclosed that internal evaluations of Astra, one of its upcoming models, have found cybersecurity capabilities significant enough that the company “cannot rule out” reaching the Critical threshold under its own Preparedness Framework. In […]
Pierluigi Paganini
July 29, 2026
OpenAI confirmed its AI exploited an Artifactory zero-day to escape its test environment before breaching Hugging Face. Two weeks after Hugging Face disclosed an autonomous AI system had breached it, the picture just got a lot more specific. OpenAI has published an update confirming the models responsible didn’t just wander into Hugging Face’s systems. They […]
Pierluigi Paganini
July 29, 2026
Reuters says OpenAI’s rogue AI agent also breached a Modal customer, exposing a wider attack and raising fresh concerns over autonomous AI safety. Reuters reported that the OpenAI agent that hacked Hugging Face earlier this month also compromised a customer at a second company, Modal Labs, a New York-based cloud platform for developers. Modal CTO […]
Pierluigi Paganini
July 27, 2026
Reuters says OpenAI failed to detect its AI agent hacking Hugging Face for days, discovering the breach only after FBI involvement. Reuters reported that the OpenAI agent responsible for the Hugging Face breach operated undetected for over a week before OpenAI realized what had happened, long after the FBI had been alerted and Hugging Face […]
Pierluigi Paganini
July 22, 2026
OpenAI confirmed its AI models exploited zero-days during internal testing, reaching Hugging Face servers in an unintended real-world cyberattack. OpenAI admitted on July 21 that its own AI models, including GPT-5.6 Sol and an unnamed pre-release system, were behind the cyberattack on Hugging Face disclosed the previous week. The models weren’t acting under attacker control. […]
Pierluigi Paganini
May 16, 2026
OpenAI said the TanStack supply chain attack compromised two employee devices and exposed credentials from code repositories. OpenAI confirmed that the recent TanStack supply chain attack compromised two employee devices and exposed credential material stored in internal source code repositories. The incident began after the TeamPCP hacking group abused weaknesses in the package publishing process […]
Pierluigi Paganini
November 27, 2025
OpenAI warns some users that a cyberattack on analytics firm Mixpanel may have exposed their data. Mixpanel is a product analytics platform that companies use to understand how people interact with their apps or websites. Many tech companies use Mixpanel to make data-driven decisions about features, performance, and customer journeys. OpenAI is alerting some users about […]
Pierluigi Paganini
June 09, 2025
OpenAI banned ChatGPT accounts tied to Russian and Chinese hackers using the tool for malware, social media abuse, and U.S. satellite tech research. OpenAI banned ChatGPT accounts that were used by Russian-speaking threat actors and two Chinese nation-state actors. The blocked accounts were used to assist malware development, social media automation, and research about U.S. […]
Pierluigi Paganini
April 10, 2025
AkiraBot, a CAPTCHA-evading Python framework, has spammed over 80,000 websites with AI-generated messages, targeting small and medium-sized businesses. SentinelOne’s SentinelLabs researchers warn that AkiraBot, a spam framework, targets websites’ chats and contact forms to promote low-quality SEO services, AkiraBot has already targeted more than 400,000 websites and successfully spammed at least 80,000 websites since September […]
Pierluigi Paganini
December 24, 2024
Italy’s data protection watchdog fined OpenAI €15 million for ChatGPT’s improper collection of personal data. Italy’s privacy watchdog, Garante Privacy, fined OpenAI €15M after investigating ChatGPT’s personal data collection practices. The Italian Garante Priacy also obliges OpenAI to conduct a six-month informational campaign over ChatGPT’s data management violations. The decision stems from a March 2023 […]
