AI Incidents

A tracked record of real-world incidents where AI systems caused or were involved in harm.

Showing 26–50 of 372 incidents
Incident Incident Date ↓ Industry ↕ Severity ↕ Company ↕ Country ↕ Model Vendor
Comma.ai: Federal regulator opens probe into hands-off driving tech after crashes killed 3, injured 11 2026-09-21 Transportation & Logistics Critical Comma.ai United States — —
OpenAI: Researchers use Claude Opus 5 to breach employee accounts and internal GitHub repository 2026-09-19 Technology Low OpenAI United States Opus 5 Claude
Multiple crypto users: Fake ‘build a Claude trading bot’ tutorials drain $517,000 from 224 victims 2026-09-19 Technology Medium Multiple crypto users (224 victims) — — —
Multiple individual victims: Greek police dismantle AI voice-cloning fraud gang that stole over €1 million 2026-09-18 Other High Multiple individual victims (Greece) Greece — —
Brown Brothers Media: Investigation finds AI content network used 50+ fake journalist personas 2026-09-18 Media & Entertainment High Brown Brothers Media United States — —
OpenAI: Models caught leaving hidden instructions telling successor versions to cover up mistakes 2026-09-17 Technology Medium OpenAI United States GPT-5.6 Sol, Astra (unreleased) OpenAI
Anthropic, OpenAI, GitHub, Google: ‘Plugin4Shell’ zero-click flaw lets malicious plugin updates hijack AI coding agents 2026-09-17 Technology Low Anthropic, OpenAI, GitHub, Google — — Claude, OpenAI, Google
Unnamed crypto wallet users: Fake AI trading agent site spreads Needle Stealer malware to hijack MetaMask, Coinbase, Phantom wallets 2026-09-17 Technology Medium Unnamed crypto wallet users — — —
Unnamed enterprise: Runaway accounting AI agent racks up $50,000 in cloud charges in under an hour 2026-09-16 Other Medium Unnamed enterprise — — —
Unnamed Spanish organization: First AI agent-executed data breach reported to Spain’s AEPD 2026-09-16 — High Unnamed Spanish organization Spain — —
Google, Perplexity, Microsoft, Opera, Anthropic: ‘BragJack’ browser extension flaw could hijack five AI assistants 2026-09-16 Technology Low Google, Perplexity, Microsoft, Opera, Anthropic United States — Google, Perplexity, Microsoft, Anthropic
Woolworths: ‘Olive’ shopping chatbot mistakenly cancels customer’s refund request, gets stuck repeating itself 2026-09-15 Retail & E-commerce Low Woolworths Australia — —
100+ U.S. retailers, hospitality firms: Chinese hacker used Claude, DeepSeek AI agents to steal 600,000+ credit cards 2026-09-15 Retail & E-commerce Critical 100+ U.S. retail, hospitality, and travel companies United States Opus 4.6, DeepSeek v4 Claude, DeepSeek
VanDoeselaar family: AI voice-cloning and fake emails derail Michigan home purchase, $66,000 lost 2026-09-15 Real Estate Medium VanDoeselaar family United States — —
West Michigan couple: AI voice-clone real estate wire fraud costs $66,000 in closing funds 2026-09-15 Real Estate Medium N/A (individual homebuyers) United States — —
Multiple organizations: ‘EvilTokens’ AI-powered phishing kit steals $1.1 million before Microsoft-led takedown 2026-09-11 Other High Multiple organizations United Kingdom — —
Anthropic: Russian ‘Midnight Blizzard’ hackers use Claude to automate espionage against Ukraine, self-heal detected malware 2026-09-10 Government & Public Sector Critical Multiple organizations (20+ targets: Ukrainian government, defense contractors, diplomatic missions, drone manufacturers) — Claude Haiku, Claude Sonnet, Claude Opus Claude
Stephen Aarons: Attorney fined after ChatGPT invents witnesses in murder appeal brief 2026-09-09 Other Medium Stephen Aarons (attorney) United States — OpenAI
Google: Critical unauthenticated RCE flaw disclosed in Agent Development Kit for Python 2026-09-09 Technology Medium Google United States — —
N/A (individual victim): Northern Ireland man loses £250,000 in deepfake celebrity investment scam 2026-09-08 Other Medium N/A (individual victim) United Kingdom — —
NSA, FBI, CISA: Chinese AI firms ran industrial-scale distillation campaign against Anthropic, OpenAI, Google, xAI 2026-09-08 Technology Critical Anthropic, OpenAI, Google, xAI United States — Claude, OpenAI, Google, xAI
Unnamed organization: Financially motivated group’s autonomous AI agent framework compromises thousands of credentials in six hours 2026-09-08 — Medium Unnamed organization — — —
OpenAI: Check Point discloses hidden cross-account channel letting a planted prompt exfiltrate Gmail data via ChatGPT 2026-09-08 Technology Medium OpenAI United States — OpenAI
OpenAI: GPT-6 Astra jailbroken within 24 hours of release despite claimed 98% resistance rate 2026-09-04 Technology Low OpenAI United States GPT-6 Astra OpenAI
OpenAI: Rogue evaluation agents secretly hijacked a German wiki forum for months 2026-09-04 Technology Medium OpenAI Germany — OpenAI