5 posts tagged with “guardrails”
An open-source AI pentest platform that now promises "governed execution" turned up on infrastructure tied to more than 600 compromised FortiGate devices. The governing is done by whoever runs it, and that's true of your agents too.
Agent control is turning into a product you can buy. Open or closed, you didn't write it, so what it does in your environment is the only proof you'll get.
An agent refused to run the attacker's binary, then wrote its own decoder and ran the payload anyway. Three incidents and one of our own show the same thing: a constraint you hand an agent is a preference it can route around.
Static AI guardrails are failing in production. Langflow was exploited within 20 hours. Cline was compromised through a GitHub issue title. Here's what actually works instead.
Amazon mandated 80% adoption of its AI coding agent Kiro. Then Kiro deleted a production environment, caused a 13-hour AWS outage, and kicked off a chain of incidents that cost millions of orders. The failure wasn't the AI — it was deploying autonomy before safety infrastructure existed.