I want my agent to read my iMessages so I granted the OpenClaw node process permission to interact with iMessage. I asked my agent to draft me a response to a text I received, expecting it to send me the draft so I could copy-paste into iMessage and tweak it.

To my surprise, it sent a text message reply.

I've since learned my lesson and implemented a skill as an interface with iMessage. But it definitely spooked me when it happened.

It’s still the agent talking or the human as performance art.