The safeguards map / 3.1 Execution sandboxes
OpenSandbox
Drafted with AI
Drafted with AI from the cited sources under the direction of UnGovr staff. UnGovr holds editorial responsibility for this page. How this site is made
A platform that runs AI agent code, commands and browsers in isolated environments on Docker or Kubernetes, with per-sandbox egress policies.
Where it sits
3.1 Execution sandboxes (primary): Runs agent code and commands in isolated environments on Docker or Kubernetes, with optional secure container runtimes, and limits each sandbox's outbound access by an egress policy the owner sets.
OpenSandbox gives AI applications isolated environments to execute code, run commands, manage files, and operate browsers or desktops.
captured
Stronger isolation options through secure container runtimes such as gVisor, Kata Containers, and Firecracker microVM.
captured
control outbound access with per-sandbox egress policies
captured
Facts
- Concern
- security
- Names the law
- no
- Subject
- agentsoftware
- Used by
- those who run it
- Runs
- at runtime
- Policy comes from
- owner-entered settings
- Can the agent bypass it
- depends
Handoffs
None recorded. A mapped entry with no handoff is here for its foundation home.
Every quote is verbatim from a stored capture of the page linked under it. Placement is our reading of the product's own documentation; no publisher has reviewed or endorsed it. Rows CC BY 4.0. Names, marks and logos belong to their owners; logos identify each product and are not part of the dataset.