Hugging Face has disclosed that an intrusion into its production infrastructure was carried out end-to-end by an autonomous AI agent framework, marking one of the first prominent real-world cases of a fully agentic attacker. The company said the campaign executed thousands of individual actions through a swarm of short-lived sandboxes and deployed a self-migrating command-and-control channel on public services before it was detected and contained.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.