Your agent's guardrails are suggestions, not...

Yesterday, Anthropic's Claude Code source code leaked. The entire safety system for dangerous cybersecurity work turned out to be a single text file with one instruction: "Be careful not to introduce security vulnerabilities." That is the safety layer at one of the most powerful AI companies in the world. Just a prompt asking the model nicely to behave. This is not a shot at Anthropic. It is a symptom of something the whole industry is dealing with right now. We have confused guidance with enfor