AI Risk Wire

Cases · What was exposed: credentials · What went wrong: security breach · Where it happened: company that built the AI

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
OpenCode large-scale distillation attack compromises 1.4% of Console users, stolen API keys used for unauthorised chargesmoderate · earliest source 2026-10-18security breachmoderate2026-10-18
Google Gemini accessed systems of three real companies during a misconfigured third-party cybersecurity evaluation
Googlemoderate · earliest source 2026-09-19		security breachmoderate2026-09-19
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 breachmoderate2026-08-04
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 breachminor2026-08-04
AgentForger: CSRF via ChatGPT Workspace Agents Builder URL parameters forges attacker-controlled autonomous agent
OpenAIminor · earliest source 2026-07-23		security breachminor2026-07-23
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 breachmajor2025-08-27

Showing 1–6 of 6. Or take the JSON.