We told OpenClaw to rm -RF and it failed successfully

Show HN: We told OpenClaw to rm -RF and it failed successfully

Operating in show hn launch, We told OpenClaw to rm -RF and it failed successfully operates.

Profile

As we all know, OpenClaw is awesome precisely because it gives us Simon Willison’s lethal trifecta: Access to private data, exposure to untrusted content, and the ability to externally communicate.While extremely risky, it gives us a glimpse of the future we can have if we actually could trust agents.To date, sandboxing (or buying mac-minis) has been the approach to reducing risk. While necessary, sandboxes also make the agent less useful because they ultimately contain and restrict the agent's helpful capabilities.To wrangle OpenClaw, we took a complementary approach. Instead of just a perimeter, we built an open source OpenClaw extension that creates deterministic lanes for the agent using

Within the show hn launch space, the company focuses on its core offering rather than a broad product line.

Directory data places it at the Show HN launch stage.

Website: securetrajectories.substack.com/p/openclaw-rm-rf-policy-as-code