
The guard that approved because it could not see the process
A sandbox hid the central process PID, the config it read was the wrong file and the routes table arrived empty. The guard still said OK.
5 posts

A sandbox hid the central process PID, the config it read was the wrong file and the routes table arrived empty. The guard still said OK.

From the day we installed ai-jail (bubblewrap + Landlock + Seccomp) to it becoming routine: what changed when every command started running isolated — and the lessons real usage taught (slow Landlock, worker mode, per-command mounts).

The autopoietic agent with ToolUse, an MCP server and a hybrid sandbox is the biggest attack surface in my ecosystem. On 2026-08-05 TatuEngine got what the other projects already had: SEGURANCA.md v1.0, a 24h watchdog, and a rule that changes how the project is developed.

When your engine runs AI-generated code, you need a sandbox that doesn't hinder development but won't let path traversal slip through.

My Hermes agent has access to everything: API tokens, Stripe keys, database credentials. One wrong terminal() command and it all leaks. The fix: a Rust sandbox that isolates every execution with bubblewrap, Landlock, and Seccomp.