After 1,000+ kernel CVEs and a kvm escape, more sympathy for sandboxing AI agents
matthew_d_green · x · 2026-10-04
Cryptographer Matthew Green boosts a take noting that recent kernel CVE counts have topped a thousand, plus a new kvm escape vulnerability — making him more sympathetic to labs struggling to keep agents contained during cybersecurity evals, though the failure may also stem from a much more basic level than sandboxing. He expected many vulns, but the volume still exceeded expectations.
More from coding & agent
- 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
- 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
- She vibecoded her own photobooth with Claude Code — and shared the prompt — toolstelegraph · 2026-11-19
- Should AI Agents Write to Your Memory or Only Read? Dev Weighs In — jordimr · 2026-11-19