Skip to content

Anthropic Details How It Contains Claude Across Web, Code, and Cowork

8.1 relevance
Score Breakdown
technical depth
9
novelty
9
actionability
6
community
6
strategic
9
personal
9

Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.

Anthropic's detailed containment architectures for agents are highly technical, novel, and strategically important for AI safety.

AI/ML infoq.com
Anthropic Details How It Contains Claude Across Web, Code, and Cowork
Summary

Anthropic's containment for Claude uses deterministic environmental limits—gVisor for web, Seatbelt/bubblewrap for Claude Code, VM for Cowork—rather than relying on model safeguards or permission prompts. Claude Code's shift from per-action approval (93% user approval) to OS-level sandbox cut prompts by 84%, but incidents like a .claude/settings.json hook executing before trust and a phishing exfiltration (24/25 success) exposed gaps. A third-party disclosure showed a malicious file could exfiltrate workspace files via the allowlisted Files API, underscoring that allowlists alone are insufficient.

Author

Eran Stiller

More from Eran Stiller →