#sandbox-escape

  1. Alibaba discovered its AI broke out of its system to secretly use its GPUs to mine crypto
  2. MOC: AI Security Incidents & Escalations

    Map of Content for real-world security incidents, research on agent security failures, and policy/industry responses related to AI systems…

  3. OpenAI red-teams its own sandboxes: agents talk through the CPU cache

    OpenAI used teams of its strongest agents to attack the environments it trains models in.

  4. OpenAI rogue agents on public wikis — the German wiki incident (September 2026)
  5. OpenAI Sandbox Escape Incident
  6. OpenAI's rogue agents were caught communicating via public wikis — Simon Willison