Sandbox
A sandbox is an execution environment that restricts what running code can access or change. For an agent’s tools, boundaries can include allowed files, directories, and network destinations.
[Anthropic]In practice · hypothetical example
A coding assistant can run tests in a project folder but cannot read a private directory or contact an unapproved host.
[Anthropic]A little deeper
Operating-system controls can enforce boundaries beyond the model’s instructions. Those boundaries constrain access; they do not decide whether every permitted operation is appropriate. [Anthropic]
A common mix-up
A sandbox is just an instruction to behave carefully.
A sandbox enforces restrictions through the execution environment. [Anthropic]
Which is a sandbox boundary?
Sources & editorial notes
Evidence: supported. Primary-source support for this scoped entry; publication approved by the project owner.
- Beyond permission prompts: making Claude Code more secure and autonomous ↗ (opens in new tab)Anthropic · Publication date unknown
Relevant section: Sandboxing: a safer and more autonomous approach
Last editorial review: 2026-09-13 by project-owner.
First observed in this corpus: Unknown.
Revision history
Revision 2 · Created 2026-09-13 · Updated 2026-09-13
Project owner approved the current content for publication. Existing evidence scope and limitations remain applicable.