Search: “OpenAI internal model”

85 stories

Searchkeyword smart Sortlatest hot importance relevance

DomainAll Cyber AIWindow24h 3d 7d 30d AllIn the wild Important only Show duplicates

CategoryAll AI safety & security 90 Vulnerability 85 Exploit / PoC 69 Data breach 36 AI industry 35 Malware 30 Ransomware 25 Threat actor 24 Policy & legal 23 Model release 16 Phishing & fraud 10 Industry 9 AI research 7 AI policy 6

SeverityAll critical 185 high 62 medium 96 low 25 info 109

LangSmith Bug Could Expose OpenAI Keys and User Data via Malicious Agents

The Hacker NewsJun 17, 17:37 UTC · Jun 17, 2025Vulnerability

30

OpenAI locks down Astra over potential critical cyber capabilities

Help Net SecurityAug 10, 00:00 UTC · Aug 10, 2026Vulnerability

55

Thousands of servers hacked in ongoing attack targeting Ray AI framework

Ars Technica · SecurityMar 27, 22:40 UTC · Mar 27, 2024Vulnerability

42

Friday Squid Blogging: Squid Washing Up on Cape Cod Beach

Schneier on SecurityJul 17, 21:01 UTC · Jul 17, 2026Vulnerability

42

Forget the model. When it comes to cybersecurity, it’s all about the harness

CyberScoopJul 16, 14:41 UTC · Jul 16, 2026Vulnerability1

55

Make OpenAI’s models misbehave and earn a reward

Help Net SecurityMar 27, 00:00 UTC · Mar 27, 2026Vulnerability

30

Anthropic Reveals Claude Escaped Testing, Breaching Three Companies

Infosecurity MagazineJul 31, 08:35 UTC · Jul 31, 2026Vulnerability

55

Protos AI delivers agent-driven threat intelligence without vendor lock-in

Help Net SecurityMar 24, 00:00 UTC · Mar 24, 2026Vulnerability in the wild

60

OpenAI Previews GPT-5.6 Sol With Restricted Access and Stronger Cyber Safeguards

The Hacker NewsJun 27, 12:20 UTC · Jun 27, 2026Vulnerability

55

⚡ Weekly Recap: Hot CVEs, npm Worm Returns, Firefox RCE, M365 Email Raid & More

The Hacker NewsDec 2, 05:36 UTC · Dec 2, 2025Vulnerability CVE-2025-59287 CVE-2025-12972 CVE-2025-12970+17 CVEs1

47

OpenAI To Extend Cyber Program to Government Agencies

Infosecurity MagazineMay 4, 08:00 UTC · May 4, 2026Vulnerability

55

GitHub Cuts Public Bug Bounty Payouts, Moves Top Rewards to VIP Tier

The Hacker NewsJul 23, 04:14 UTC · Jul 23, 2026Vulnerability

55

US companies commit to safe, transparent AI development

Help Net SecurityMar 18, 11:15 UTC · Mar 18, 2025Vulnerability

30

Anthropic to put AI in charge of reviewing Claude Code actions by default

Help Net SecurityAug 10, 00:00 UTC · Aug 10, 2026Vulnerability1

55

Week in review: Notepad++ supply chain attack details and targets, Patch Tuesday forecast

Help Net SecurityFeb 8, 00:00 UTC · Feb 8, 2026Vulnerability in the wildCVE-2026-21509 CVE-2025-22225 CVE-2026-24423

60

Is Agentic AI too smart for your own good?

Help Net SecuritySep 9, 09:52 UTC · Sep 9, 2025Vulnerability

55

Microsoft Launches Flurry of AI Security Initiatives

Infosecurity MagazineJul 28, 12:45 UTC · Jul 28, 2026Vulnerability

30

OpenAI Unveils Aardvark: GPT-5 Agent That Finds and Fixes Code Flaws Automatically

The Hacker NewsOct 31, 17:19 UTC · Oct 31, 2025Vulnerability

55

XM Cyber advances AI security with enhanced exposure and attack path visibility

Help Net SecurityMar 25, 09:46 UTC · Mar 25, 2026Vulnerability

55

Time to keep up with AI-driven attacks is narrowing, OpenAI says

Help Net SecurityApr 29, 00:00 UTC · Apr 29, 2026Vulnerability

55

M365 Copilot: New Zero-Click AI Flaw Allows Corporate Data Theft

Infosecurity MagazineJun 13, 10:15 UTC · Jun 13, 2025Vulnerability1

55

⚡ Weekly Recap: IoT Exploits, Wallet Breaches, Rogue Extensions, AI Abuse & More

The Hacker NewsJan 5, 12:56 UTC · Jan 5, 2026Vulnerability CVE-2025-55182 CVE-2025-13915 CVE-2025-52691+7 CVEs

60

Single Prompt Enables ChatGPT to Execute Full Cyber

Infosecurity MagazineJul 16, 13:30 UTC · Jul 16, 2026Vulnerability

30

Iran’s AI Ambitions: National Security, Global Influence, and Strategic Challenges

Recorded FutureAug 22, 00:00 UTC · Aug 22, 2025Vulnerability

55

OpenAI’s GPT-5.5 is out with expanded cybersecurity safeguards

Help Net SecurityApr 24, 00:00 UTC · Apr 24, 2026Vulnerability

30

Whitepaper: Securing GenAI

Help Net SecurityAug 14, 09:50 UTC · Aug 14, 2025Vulnerability

30

The AI security crisis no one is preparing for

Help Net SecurityAug 20, 00:00 UTC · Aug 20, 2025Vulnerability

55

Impact of generative AI on cybersecurity: facts and predictions

Kaspersky SecurelistDec 11, 10:00 UTC · Dec 11, 2023Vulnerability

30

Does Anthropic deserve the trust of the cybersecurity community?

Help Net SecurityMar 12, 00:00 UTC · Mar 12, 2026Vulnerability

55

Training an AI agent to attack LLM applications like a real adversary

Help Net SecurityMar 25, 00:00 UTC · Mar 25, 2026Vulnerability

42

AI-as-a-Service Providers Vulnerable to PrivEsc and Cross

The Hacker NewsApr 8, 04:08 UTC · Apr 8, 2024Vulnerability

55

Week in review: Cisco SD-WAN 0-day exploited, Patch Tuesday forecast

Help Net SecurityJun 7, 00:00 UTC · Jun 7, 2026Vulnerability in the wildCVE-2026-0257 CVE-2026-41089 CVE-2025-48595+1 CVEs

60

Why the “voluntary AI commitments” extracted by the White House are nowhere near enough

Help Net SecurityAug 16, 00:00 UTC · Aug 16, 2023Vulnerability

55

Google Expands Its Bug Bounty Program to Tackle Artificial Intelligence Threats

The Hacker NewsOct 27, 14:38 UTC · Oct 27, 2023Vulnerability

42

AI systems ‘subject to new types of vulnerabilities,’ British and US cyber agencies warn

The RecordNov 28, 13:29 UTC · Nov 28, 2023Vulnerability

30

Over 225,000 Compromised ChatGPT Credentials Up for Sale on Dark Web Markets

The Hacker NewsMar 8, 05:58 UTC · Mar 8, 2024Vulnerability

42

U.S. Orders Anthropic to Suspend Fable 5 and Mythos 5 Access for Foreign Nationals

The Hacker NewsJun 15, 00:00 UTC · Jun 15, 2026Vulnerability

55

DIG AI: Uncensored darknet AI assistant at the service of criminals and terrorists

Help Net SecurityDec 22, 00:00 UTC · Dec 22, 2025Vulnerability

42

US lifts export controls on Anthropic’s frontier cybersecurity AI models

The RecordJul 1, 13:22 UTC · Jul 1, 2026Vulnerability

55

Week in review: Cisco patches SD-WAN 0-day, unpatched Microsoft Exchange Server flaw exploited

Help Net SecurityMay 17, 00:00 UTC · May 17, 2026Vulnerability in the wildCVE-2026-44413 CVE-2026-41940 CVE-2026-46300+2 CVEs1

60