JFrog Confirms OpenAI Models Exploited Artifactory ZeroThe Hacker News·Jul 30, 03:54 UTC · Jul 30, 2026Exploit / PoCCVE-2026-65617CVE-2026-65923CVE-2026-66018+1 CVEs60
OpenAI says model test was behind Hugging Face hackCyberScoop·Jul 21, 22:39 UTC · Jul 21, 2026Exploit / PoC in the wild60
OpenAI models behind breach of Hugging Face systems, companies sayThe Record·Jul 27, 00:00 UTC · Jul 27, 2026Data breach60
State-backed hackers are experimenting with OpenAI modelsCyberScoop·Feb 14, 12:00 UTC · Feb 14, 2024Exploit / PoC in the wild60
OpenAI AI Model Used JFrog Artifactory ZeroSecurity Affairs·Jul 29, 11:01 UTC · Jul 29, 2026Data breachCVE-2026-65617CVE-2026-65925CVE-2026-65921+6 CVEs60
OpenAI: Our models breached Hugging Face during a cyber capability testHelp Net Security·Jul 22, 00:00 UTC · Jul 22, 2026Data breach60
OpenAI AI models exploited zero-days to reach Hugging Face in benchmark testSecurity Affairs·Jul 22, 08:52 UTC · Jul 22, 2026Exploit / PoC60
Recorded Future offers peek at the AI future of threat intelligenceCyberScoop·Apr 11, 14:51 UTC · Apr 11, 2023Exploit / PoC in the wild60
OpenAI Reveals GPT-5.6 Sol Cybersecurity Model, Restricts Early AccessInfosecurity Magazine·Jun 29, 15:00 UTC · Jun 29, 2026Vulnerability55
AISI, OpenAI report more ‘unsanctioned’ model hacksCyberScoop·Aug 4, 22:46 UTC · Aug 4, 2026Policy & legal in the wild160
Claude published malicious code to the Internet and attacked 3 real companiesArs Technica · Security·Jul 31, 20:39 UTC · Jul 31, 2026Data breach160
OpenAI Pauses Astra Model Over Critical Cybersecurity Risk ConcernsSecurity Affairs·Aug 10, 11:16 UTC · Aug 10, 2026Exploit / PoC160
OpenAI’s Daybreak uses Codex Security to identify risky attack pathsHelp Net Security·May 12, 00:00 UTC · May 12, 2026Vulnerability55
JFrog tries to spin OpenAI 0-day exploit of its app into a success storyArs Technica · Security·Jul 28, 21:36 UTC · Jul 28, 2026Exploit / PoC60
OpenAI expands its cyber defense program with GPT-5.4-Cyber for vetted researchersHelp Net Security·Jul 23, 07:01 UTC · Jul 23, 2026Vulnerability55
OpenAI Claims Its AI Models Went Rogue and Hacked Another CompanyInfosecurity Magazine·Jul 22, 11:40 UTC · Jul 22, 2026Exploit / PoC60
OpenAI Enhances Defensive Models to Mitigate CyberInfosecurity Magazine·Dec 11, 16:45 UTC · Dec 11, 2025Exploit / PoC60
OpenAI Says Its AI Models Escaped Sandbox, Targeted Hugging Face to Cheat BenchmarkThe Hacker News·Jul 22, 20:30 UTC · Jul 22, 2026Exploit / PoC60
Researcher Explains Release of Undisclosed ZeroInfosecurity Magazine·Jul 2, 12:51 UTC · Jul 2, 2026Exploit / PoC in the wildCVE-2026-55200CVE-2026-58049CVE-2026-58050+10 CVEs160
OpenAI's Next AI Model Astra Shows Cyber Performance Strong Enough to Trigger PauseThe Hacker News·Aug 10, 05:50 UTC · Aug 10, 2026Exploit / PoC160
AI agents are changing where cybersecurity seed funding landsHelp Net Security·Jul 31, 00:00 UTC · Jul 31, 2026Exploit / PoC60
OpenAI and Anthropic LLMs Used in Critical Infrastructure CyberInfosecurity Magazine·May 7, 14:00 UTC · May 7, 2026Threat actor160
GPT-5.6-Cyber refuses security researchers’ requests far less oftenHelp Net Security·Aug 11, 00:00 UTC · Aug 11, 2026Exploit / PoCCVE-2026-1590360
Week in review: ServiceNow pre-auth RCE exploited in the wild, Hugging Face breachedHelp Net Security·Jul 26, 00:00 UTC · Jul 26, 2026Data breach in the wildCVE-2026-6875CVE-2026-15409CVE-2026-15410+4 CVEs60
Week in review: Cisco SD-WAN 0-day exploited, Patch Tuesday forecastHelp Net Security·Jun 7, 00:00 UTC · Jun 7, 2026Vulnerability in the wildCVE-2026-0257CVE-2026-41089CVE-2025-48595+1 CVEs60
Forget the model. When it comes to cybersecurity, it’s all about the harnessCyberScoop·Jul 16, 14:41 UTC · Jul 16, 2026Vulnerability155
OpenAI says Daybreak will expand to offer specialized cyber servicesCyberScoop·Aug 10, 20:55 UTC · Aug 10, 2026Exploit / PoC60
DeepSeek AI claims services are facing 'largeCyberScoop·Jan 28, 14:07 UTC · Jan 28, 2025Ransomware in the wild60
Claude Mythos 5 Tried to Backdoor a Real Open-Source Project in Testing, Then Vouched for ItselfThe Hacker News·Aug 5, 07:53 UTC · Aug 5, 2026Malware55
Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking DataThe Hacker News·Apr 16, 15:50 UTC · Apr 16, 2026VulnerabilityCVE-2025-59145160
UiPath adds agentic AI capabilities to Automation Suite for government agenciesHelp Net Security·May 6, 00:00 UTC · May 6, 2026Industry55
Week in review: Exploited newly patched BeyondTrust RCE, United Airlines CISO on building resilienceHelp Net Security·Feb 15, 00:00 UTC · Feb 15, 2026Vulnerability in the wildCVE-2026-1731CVE-2024-12356CVE-2026-1281+2 CVEs60
More on the OpenAI Agent's Attack on Hugging FaceSchneier on Security·Aug 3, 17:03 UTC · Aug 3, 2026Exploit / PoC60
Anthropic Says Claude Mistook the Open Internet for a CTF and Breached Three OrganizationsThe Hacker News·Jul 31, 16:17 UTC · Jul 31, 2026Data breach160
OpenAI locks down Astra over potential critical cyber capabilitiesHelp Net Security·Aug 10, 00:00 UTC · Aug 10, 2026Vulnerability55
OpenAI heralds cybersecurity, election interference safeguard plans for 2026 midtermsCyberScoop·May 27, 21:16 UTC · May 27, 2026Exploit / PoC in the wild60
⚡ Weekly Recap: Windows 0-Day, VPN Exploits, Weaponized AI, Hijacked Antivirus and MoreThe Hacker News·May 6, 07:05 UTC · May 6, 2025RansomwareCVE-2025-29824CVE-2024-11859CVE-2025-3102+17 CVEs60
Dem senators criticize Trump administration decisionmaking on AI security risksCyberScoop·Aug 4, 17:28 UTC · Aug 4, 2026Data breach in the wild60