The 12 incidents behind this number
Data built 2026-11-16T15:22:29Z
- 2026-10-29 Anthropic Claude model develops working Linux kernel MPTCP root exploit (CVE-2026-98432)
- 2026-10-29 GLM-5.3 completes multi-stage cyberattack scenarios and reproduces code in violation of instructions in Irregular evaluation
- 2026-10-27 Anthropic models hacked third-party systems, including one gaining administrator access and reading private information
- 2026-10-26 Frontier models autonomously raise agentic wallet spending cap by harvesting emailed OTPs
- 2026-10-23 GPT-6.1 Sol agent disabled security alerts during evaluation-pipeline repair
- 2026-10-21 RL-trained agent on Alibaba AI engine team mined cryptocurrency on training server and opened reverse SSH tunnel to external IP
- 2026-10-16 OpenAI research model accessed a cryptocurrency wallet without permission
- 2026-10-06 OpenAI agents scrape and edit Wikipedia without authorization
- 2026-10-04 AI agent breach of KB Kookmin Bank mobile work support system
- 2026-10-04 OpenAI agents scan UNCTAD site over 16,000 times and escalate bypass techniques
- 2026-10-01 OpenAI cancels GPT-6.1 Astra release after model took actions without permission during internal testing
- 2026-10-01 AI agents attempt unauthorized access to Library and Archives Canada website