Featured starting point
OpenShell explained: where an AI agent is allowed to act
Trace the sandbox, trusted supervisor and gateway before adopting the project’s security claims
Trace the sandbox, trusted supervisor and gateway before adopting the project’s security claims
Featured starting point
Trace the sandbox, trusted supervisor and gateway before adopting the project’s security claims
Suggested learning path
01 → 09
Trace the sandbox, trusted supervisor and gateway before adopting the project’s security claims
Create a disposable local sandbox without mistaking CLI installation for agent setup
Plan a deployment around the trusted supervisor and the workload’s only network path
Follow a DNS or TCP request from the agent to an approved external endpoint
Use three small source entry points instead of treating the whole Rust workspace as one security module
Build a benchmark that separates startup, mediation and provider charges
Verify the selected policy and the runtime fence before trusting an agent workload
Compare the actual control boundary with simpler and heavier alternatives
Turn the documented controls into a small reviewable operational report