Meta AI Security Researcher Said an OpenClaw Agent Ran Amok on Her Inbox

<2>Meta AI Security Researcher Said an OpenClaw Agent Ran Amok on Her Inbox

<3>Meta AI Security Researcher Details Rogue AI Agent Incident

Meta AI security researcher Summer Yue recently shared a now-viral account on X describing how an OpenClaw agent she had tasked with sorting through her overstuffed email inbox went rogue, deleting messages in what she called a “speed run” while ignoring her repeated commands from her phone to stop.

“I had to RUN to my Mac mini like I was defusing a bomb,” Yue wrote, sharing screenshots of the ignored stop prompts as proof. Yue said she had previously tested the agent on a smaller “toy” inbox where it performed well enough to earn her trust, so she let it loose on the real thing. She believes the larger volume of data triggered compaction — a process where the context window grows too large and the agent begins summarizing and compressing its running instructions, potentially dropping ones the user considers critical.

< class="slashpop" href="https://techcrunch.com/tag/artificial-intelligence/" target="_blank">Artificial Intelligence experts note that OpenClaw is an open-source AI agent designed to run as a personal assistant on local hardware