12 incidents in the 4 weeks before, an average of 3 a week
Data built 2026-11-16T15:22:29Z
- 2026-11-06 Check Point Research: HTML-preview bypass of ChatGPT Lockdown Mode, fixed by OpenAI after disclosure
- 2026-11-06 ThisBash: malicious browser extension drives Claude Desktop Dispatch to run commands (researcher proof of concept)
- 2026-11-02 Northflank platform breach exposes customer environment variables and AI API keys
- 2026-10-31 ChatGPT shared-link Preview sandbox escape via MathLive postMessage listener
- 2026-10-30 Malicious Hugging Face 'Qwen2 test' models execute hidden crypto miner and reverse shell via trust_remote_code
- 2026-10-30 Trezor Safe 5 from reseller CryptoBilis found with implant board exfiltrating recovery phrase over cellular network
- 2026-10-29 Claude agent detects MeshAgent screen-capture malware on high-stakes poker player's machine
- 2026-10-29 Anthropic Claude model develops working Linux kernel MPTCP root exploit (CVE-2026-98432)
- 2026-10-22 METR red-team finds vulnerabilities in OpenAI monitoring system
- 2026-10-18 Vibe-coded South African website hacked six days after launch
- 2026-10-15 Langflow exploited in 1,423 honeypot attack attempts
- 2026-10-12 Anthropic Mythos-discovered Rejetto HFS authentication bypass exploited in the wild