Self-spreading AI-agent malware infects 1,000+ systems in the wild
The index says: unlikely (30%). Graded on that date, right or wrong, in public.
Why the index thinks so
OpenAI showed self-replicating prompt injections that spread agent-to-agent in simulation, a self-replicating injection spread through Word documents in July, and worms already spread through coding-assistant sessions.
What would move it
Security vendor reports of prompt-injection propagation; mass compromises of agent marketplaces.