5 prompts to hack himself: Docker's microVM sandboxes for coding agents explained
AI Engineer · youtube · 2026-10-03
At AI Engineer World's Fair, Docker PM Rowan Christmas showed how his own coding agent surfaced browser history and bank data in just 5 prompts. His fix: Docker Sandboxes (sbx), one-command microVMs with isolated kernels, filesystem isolation, secret placeholders, default-deny networking and audit trails — compatible with Claude Code, Codex and more. He also previews agent identity, delegation chains and policy-based governance, with L7 and per-repo controls coming.
More from coding & agent
- FT: US tech outages blamed on rush to fix bugs found by AI — nordicinst · 2026-11-19
- Claude Code overtakes Cursor and Copilot in job-post mentions ahead of Anthropic IPO — antgoldbloom · 2026-11-19
- Dev submits PR adding periodic checkpoints to GKE sandboxes so agents don't lose progress — yoimnotkesku · 2026-11-19
- AWS adds private CA support to Bedrock AgentCore Identity for connecting agents to self-hosted IdPs — AWS ML Blog · 2026-11-19
- Orchestrator's Cloud Agents graduate from beta to general availability — julianweisser · 2026-11-19
- Zero users, 33 pages shipped: dev crowdsources audit for AI-agent trust schema — TheHamzaShahbaz · 2026-11-19