Justin Boitano

“Recent incidents have highlighted a fundamental hurdle for AI agents, and that is that model-level safeguards alone can't govern what agents can access or do,”

Justin Boitano · said date not stated · reported 2026-09-28

Boitano said recent incidents show that model-level safeguards alone cannot govern what AI agents can access or do.

“Each security incident is unique, and we have to look at all of them in detail,”

Justin Boitano · said date not stated · reported 2026-09-28

Boitano said each security incident is unique and must be examined in detail.

“From what we know, Hugging Face reported over 17,000 agents attacking their infrastructure that went on for days and weeks.”

Justin Boitano · said date not stated · reported 2026-09-28

Boitano said Hugging Face reported over 17,000 agents attacking its infrastructure over days and weeks.