Sysdig documented a ransomware operation with no human at the keyboard. An LLM broke into an exposed Langflow server, moved laterally, and encrypted a production database start to finish. The tactics were old. The operator was not a person.
Anthropic's J-space research promises something like intent telemetry for AI agents. The opportunity is real, but it is not the logs we never had: it is a noisy, adversarially fragile sensor that needs an enforcement point you should have built anyway.
Private data, untrusted content, and an exfiltration channel. When an agent has all three, someone else decides what it does with your secrets. Here is the pattern, drawn from three real breaches.
AI agents have credentials, autonomy, and total gullibility. Stop securing them like software and start securing them like staff.
Threat intelligence, offensive security, and AI security: why this blog exists and what to expect.