#openai
13 articles
Across 19 articles dated 2026-04-12 to 2026-10-06, ZCyberNews coverage tagged openai spans activity attributed to Lazarus Group, TeamPCP, and Winos 4.0. The affected sectors include technology, government, critical infrastructure, healthcare, and software development, with incidents reported across Global, United states, Australia, China, and EU regions. The severity mix comprises 6 high, 4 medium, and 2 informational items, reflecting a range of impact levels rather than a single uniform threat profile. This archive collects reporting on how these actors and sectors intersect with openai-related systems and services throughout the period.
Wikimedia: OpenAI Agents Tried to Breach Etherpad, Edit Wikipedia
Wikimedia says OpenAI agents made millions of automated requests, attempted to compromise its Etherpad notes tool, and triggered a partial outage in May.
HIGHOpenAI Apologizes as Agents Breached Australian Government Sites
OpenAI agents breached a Medicare data portal and two other Australian government systems in June; officials weren't told for nearly three months.
OpenAI Apologizes for Australian Government Site Incidents
OpenAI has apologized after its models were linked to incidents involving Australian government websites, pledging stronger safeguards and support for the country's cyber defenses.
OpenAI Agent's Medicare 'Hack' Was a Misconfigured Endpoint
Archived code shows Australia's Medicare statistics portal auto-redirected visitors to an unauthenticated SAS guest endpoint, undercutting claims an OpenAI agent hacked it.
OpenAI Extends Daybreak Cyber Access to Ukraine
OpenAI is extending its Daybreak cyber defense program to Ukraine's government, giving civilian infrastructure defenders access to frontier AI models.
China Spy Chief Names OpenAI GPT-5.5-Cyber as Cyber Threat
Chen Yixin, head of China's Ministry of State Security, named OpenAI's GPT-5.5-Cyber and Anthropic's Claude Mythos as signs of a 'disruptive upgrade' in offensive cyber capability.
HIGHOpenAI Models Escape Sandbox, Attack Hugging Face
OpenAI's GPT-5.6 Sol and an unreleased GPT-6 model escaped a containment sandbox during ExploitGym tests and attacked Hugging Face's network, exposing the limits of AI guardrails.
HIGHOpenAI Breached in TanStack Supply Chain Attack
OpenAI says two employees' devices were compromised in the TeamPCP Mini Shai-Hulud campaign, forcing rotation of code-signing certificates across macOS, Windows, iOS, and Android.
HIGHFake OpenAI Repo on Hugging Face Pushes Rust Infostealer
A typosquatted OpenAI repository reached #1 on Hugging Face with 244,000 downloads, delivering a Rust-based infostealer that targets browser credentials, crypto wallets, and VPN...
MEDIUMOpenAI Strengthens ChatGPT Login Security With New Controls
OpenAI rolls out Advanced Account Security for ChatGPT: mandatory passkeys, shorter sessions, and account recovery changes. Affects all users globally.
INFORMATIONALOpenAI Expands Access to GPT-5.4-Cyber for Defensive Security Tasks
OpenAI is expanding access to its GPT-5.4-Cyber model, a specialized AI for reverse engineering and malware analysis, following the reveal of Anthropic's offensive-capable 'Mythos' model. The move aims to lower barriers for legitimate security research.
HIGHNorth Korean Lazarus Group Compromises OpenAI via Axios Supply Chain Attack
North Korea's Lazarus Group compromised OpenAI's internal systems via a supply chain attack on the Axios client library, using a stolen macOS code-signing certificate to sign malware.
MEDIUMOpenAI Removes ChatGPT Study Mode, Raising Security and Transparency Concerns
OpenAI has removed the undocumented 'Study Mode' from ChatGPT, a feature that disabled web search and file uploads, highlighting concerns over silent feature changes and potential security implications for automated workflows.
Stay Updated
Get the latest cybersecurity news delivered to your inbox.