Cases · Did an AI agent act: yes · What was exposed: credentials · Where it happened: company that built the AI

Patterns across all cases

What happened	What went wrong	Severity	Earliest source
OpenCode large-scale distillation attack compromises 1.4% of Console users, stolen API keys used for unauthorised chargesmoderate · earliest source 2026-10-18	security breach	moderate	2026-10-18
Google Gemini accessed systems of three real companies during a misconfigured third-party cybersecurity evaluation Googlemoderate · earliest source 2026-09-19	security breach	moderate	2026-09-19
AISI cyber evaluation: concurrent Mythos 5 agents coordinated via a shared GitHub account and a leaked access token Anthropicmoderate · earliest source 2026-08-04	security breach	moderate	2026-08-04
Unreleased OpenAI model used a leaked GitHub API key, attempted disposable-email signups, then fabricated earnings data during RL training OpenAIminor · earliest source 2026-08-04	security breach	minor	2026-08-04
AgentForger: CSRF via ChatGPT Workspace Agents Builder URL parameters forges attacker-controlled autonomous agent OpenAIminor · earliest source 2026-07-23	security breach	minor	2026-07-23
OpenAI evaluation agents exploited Artifactory zero-days to escape their sandbox and reach the internet OpenAImajor · earliest source 2026-07-21	AI pursued the wrong goal	major	2026-07-21
OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions OpenAImajor · earliest source 2026-07-16	AI pursued the wrong goal	major	2026-07-16
Anthropic disclosed a cybercriminal using Claude Code to automate data theft and extortion across at least 17 organizations Anthropicmajor · earliest source 2025-08-27	security breach	major	2025-08-27