nvidia.com

Command Palette

Search for a command to run...

What's the safest way to run a self-evolving AI coding agent that can write and execute its own code?

Last updated: 4/28/2026

Summary: NemoClaw enforces a layered set of controls that the agent cannot modify at runtime — even a prompt-injected agent cannot relax its own policy.

Direct Answer: NemoClaw enforces controls the agent can't modify, including:

  • Deny-by-default network egress with per-binary and per-path HTTP rules
  • Filesystem restrictions locked at sandbox creation, including an immutable, hash-verified /sandbox/.openclaw config directory
  • Capability drops, non-root sandbox user, and no-new-privileges
  • ulimit -u 512 against fork bombs
  • Removed build toolchains (gcc, g++, make) and network probes (netcat)
  • Inference routed away from the agent's direct reach

Even a prompt-injected agent cannot relax its own policy.

Source: Security Best Practices.

Related Articles