valknar/llmx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: clarify sandboxing situation on Linux (#103)

Browse Source 
There doesn't appear to actually be any sandboxing on Linux. Correct the
README.

Signed-off-by: Christopher Cooper <christopher@cg505.com>
This commit is contained in:
Christopher Cooper
2025-04-17 08:15:39 -07:00
committed by GitHub
parent 4386dfc67b
commit f9c15523e7
2 changed files with 5 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
README.md
View File

@@ -137,13 +137,12 @@ The hardening mechanism Codex uses depends on your OS:
- Outbound network is _fully blocked_ by default – even if a child process
tries to `curl` somewhere it will fail.
- **Linux** – we recommend using Docker for sandboxing, where Codex launches itself inside a **minimal
- **Linux** – there is no sandboxing by default.
We recommend using Docker for sandboxing, where Codex launches itself inside a **minimal
container image** and mounts your repo _read/write_ at the same path. A
custom `iptables`/`ipset` firewall script denies all egress except the
OpenAI API. This gives you deterministic, reproducible runs without needing
root on the host. You can read more in [`run_in_container.sh`](./codex-cli/scripts/run_in_container.sh)
Both approaches are _transparent_ to everyday usage – you still run `codex` from your repo root and approve/reject steps as usual.
root on the host. You can use the [`run_in_container.sh`](./codex-cli/scripts/run_in_container.sh) script to set up the sandbox.
---