The safeguards map / 3.1 Execution sandboxes
Lima
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
Runs Linux virtual machines, documented for running AI agents inside a VM so they cannot directly read, write or execute the host's files.
Where it sits
3.1 Execution sandboxes (primary): Runs an AI agent inside a Linux virtual machine so it reaches the host only through the directories the owner chooses to mount, read-only or writable.
Lima is useful for running AI agents inside a VM, so as to prevent agents from directly reading, writing, or executing the host files.
captured
it is highly recommended to only mount your project directory (current directory) into the VM
captured
Facts
- Concern
- security
- Names the law
- no
- Subject
- softwareagent
- Used by
- those who run it
- Runs
- by hand
- Policy comes from
- vendor defaultsowner-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.