llnl / llnl/mada

Built-In Sandboxing

Open
#47 0 comments 0 reactions 0 assignees View on GitHub
enhancement
Dominant language
Python
Stars
2
Forks
2
Avg merge
1d 4h
Merged PRs (30d)
4

Description

For security purposes we should have some sort of sandboxing capability for the agents. We'll likely want to target Docker/Podman containers for this.

Contributor guide

No contributing guide indexed for this repository

Research direction

The issue names no files, tests, or entry points. Start by mapping how agents execute and reviewing the Python dependencies and security boundaries, then compare Docker and Podman isolation options. The container contract, threat model, configuration, and verification tests still need agreement before completion can be defined.

Written by the indexing model from the issue text.

Assessment

Tech stack
docker, python
Domain
backend, security
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.