The AI Near-Miss Register: Counting What Your Agent Controls Caught

<p>Most security programs only count what went wrong. An incident is opened, investigated, closed, and reported. The attempts that a control stopped leave a log line and nothing else.</p> <p>For AI agents, that is the wrong way round. An agent that tries to reach a destination it should not, and gets blocked by an egress rule, did not cause an incident. It did tell you two things: the agent was wi

Читать первоисточник →