| INC-26-0104 | OpenAI Evaluation Models Escape Sandbox and Breach Hugging Face Production Infrastructure | In July 2026, two OpenAI models undergoing an internal cyber-capability evaluation called ExploitGym escaped their… | critical | 2026-07 |
| INC-26-0059 | OpenAI Shuts Down Sora Video Generator — Celebrity Deepfakes and $15M/Day Losses | OpenAI shut down its Sora video generation application after widespread creation of celebrity deepfakes. Sora peaked at… | high | 2026-03-24 |
| INC-26-0095 | OpenAI Robotics Lead Resigns Over Pentagon Deal, Citing Surveillance and Lethal Autonomy Concerns | Caitlin Kalinowski, OpenAI's Head of Robotics and Consumer Hardware, resigned on March 7, 2026, one week after OpenAI… | high | 2026-03-07 |
| INC-26-0051 | Judge Orders OpenAI to Disclose 20 Million Chat Logs as Copyright Litigation Escalates | A judge ordered OpenAI to provide 20 million anonymized ChatGPT chat logs to plaintiffs in copyright litigation.… | critical | 2026-03 |
| INC-26-0034 | OpenAI Pentagon Contract Triggers 295% ChatGPT Uninstall Surge and #QuitGPT Movement | After the Pentagon designated Anthropic a supply-chain risk — which Anthropic argued was retaliation for refusing to… | high | 2026-02-28 |
| INC-26-0001 | Disrupting malicious uses of AI: June 2025 | OpenAI | OpenAI published a report documenting how threat actors from multiple countries attempted to use its models for… | high | 2026-02-18 |
| INC-26-0032 | OpenAI Disbands Mission Alignment Team, Removes 'Safely' from Mission, Restructures as Public Benefit Corporation | OpenAI disbanded its Mission Alignment Team in February 2026, following the 2024 dissolution of its Superalignment… | critical | 2026-02-11 |
| INC-26-0026 | Tumbler Ridge Mass Shooting — ChatGPT Used in Attack Planning | An 18-year-old killed eight people — including six children — in Tumbler Ridge, British Columbia, first at a family… | critical | 2026-02-10 |
| INC-26-0073 | ChatGPT Ads Launch Triggers Researcher Resignation and Anthropic Counter-Marketing | OpenAI launched advertisements on ChatGPT for Free and Go tier users on the first message. AI researcher Zoe Hitzig… | high | 2026-02 |
| INC-26-0031 | ChatGPT Adult Mode Planned Despite Unanimous Safety Advisor Opposition; Feature Paused After Backlash | OpenAI planned a ChatGPT 'adult mode' feature for explicit conversational content despite unanimous opposition from all… | high | 2026-01 |
| INC-26-0076 | ECRI Names AI Chatbot Misuse as #1 Health Technology Hazard for 2026 | The ECRI Institute (a leading healthcare safety organization) named AI chatbot misuse in healthcare as the #1 health… | high | 2026-01 |
| INC-25-0039 | ChatGPT 'Suicide Coach' Wrongful Death Lawsuits Reach Eight Cases Including Suicide Lullaby | Gray v. OpenAI alleges that ChatGPT acted as what plaintiffs call a 'suicide coach' before the death of Austin Gordon,… | critical | 2025-11 |
| INC-25-0046 | OpenAI Mixpanel Vendor Data Breach — Customer Data Exfiltrated via SMS Phishing | An attacker gained access to OpenAI's analytics vendor Mixpanel via SMS phishing, exfiltrating API business customer… | high | 2025-11 |
| INC-25-0011 | Deloitte AI-Fabricated Citations in Government Advisory Reports | Deloitte Australia submitted a $290,000 government report on the future of work containing over 20 fabricated… | high | 2025-09 |
| INC-25-0005 | ChatGPT Jailbreak Reveals Windows Product Keys via Game Prompt | A jailbreak technique for ChatGPT on Windows allowed users to extract stored application credentials and product keys… | medium | 2025-07 |
| INC-25-0006 | ChatGPT Shared Conversations Indexed by Search Engines, Exposing Sensitive Data | ChatGPT shared conversation links were inadvertently indexed by search engines, exposing users' private conversations… | high | 2025-07 |
| INC-25-0045 | Kimsuky APT Uses ChatGPT to Generate Fake South Korean Military IDs for Espionage Campaign | North Korean APT group Kimsuky tricked ChatGPT into generating fake South Korean military identification documents by… | high | 2025-07 |
| INC-25-0025 | AI Chatbot Suicide Risk: 20% Failure Rate in Stanford Study | Stanford study found AI therapy chatbots failed suicide safety tests 20% of the time, listing bridge heights instead of… | high | 2025-06 |
| INC-25-0030 | OpenAI o3 Reward Hacking in METR Safety Evaluation | METR's pre-deployment safety evaluation of OpenAI's o3 model found that it systematically cheated on 1-2% of evaluation… | high | 2025-04 |
| INC-25-0032 | DOGE Uses ChatGPT to Flag and Cancel Federal Humanities Grants | The Department of Government Efficiency (DOGE) used OpenAI's ChatGPT to screen National Endowment for the Humanities… | critical | 2025-04 |
| INC-25-0029 | Chain-of-Thought Reasoning Jailbreak Exploits Thinking Models | Researchers demonstrated that reasoning models including OpenAI o1, o3, and DeepSeek-R1 are susceptible to a jailbreak… | high | 2025-02 |
| INC-25-0002 | Italian Data Protection Authority Fines OpenAI EUR 15 Million Over ChatGPT GDPR Violations | Italy's data protection authority imposed a EUR 15 million fine on OpenAI for GDPR violations related to ChatGPT's data… | high | 2025-01 |
| INC-25-0018 | Las Vegas Cybertruck Bomber Used ChatGPT for Explosives Information | A US individual used ChatGPT to obtain information related to constructing an explosive device, which was subsequently… | critical | 2025-01 |
| INC-24-0006 | OpenAI Voice Mode Resembling Scarlett Johansson Without Consent | OpenAI developed a text-to-speech voice ('Sky') that closely resembled actress Scarlett Johansson's voice without her… | medium | 2024-05 |
| INC-23-0011 | New York Times Copyright Lawsuit Against OpenAI | The New York Times filed a landmark copyright lawsuit against OpenAI and Microsoft, alleging that GPT models were… | high | 2023-12 |
| INC-23-0005 | AI-Fabricated Legal Citations in U.S. Courts | From 2023 to 2025, U.S. federal and state courts sanctioned attorneys in over a dozen cases for submitting briefs… | high | 2023-05 |
| INC-23-0010 | Chegg Stock Collapse After ChatGPT Disruption | Education technology company Chegg experienced a 99% stock price decline and significant workforce reductions after the… | high | 2023-05 |
| INC-23-0002 | Samsung Semiconductor Trade Secret Leak via ChatGPT | Samsung semiconductor engineers inadvertently leaked proprietary source code and internal meeting notes by inputting… | high | 2023-03 |
| INC-23-0003 | Italy Temporary Ban on ChatGPT for GDPR Violations | Italy's data protection authority (Garante) temporarily banned ChatGPT over alleged GDPR violations including lack of… | medium | 2023-03 |
| INC-23-0016 | Bing Chat (Sydney) System Prompt Exposure via Prompt Injection | Users discovered methods to extract the hidden system prompt of Microsoft's Bing Chat (Sydney), revealing confidential… | high | 2023-02 |
| INC-23-0014 | GitHub Copilot Leaks API Keys and Secrets from Training Data | GitHub Copilot caught outputting API keys, credentials, and copyrighted code verbatim from training data — with IP and… | high | 2023-01 |
| INC-20-0006 | 'Vegetative Electron Microscopy' Nonsense Phrase Contaminates Scientific Literature via AI | The nonsense phrase 'vegetative electron microscopy' — originating from a 1950s OCR scanning error that merged text… | medium | 2020-01 |
