Developer Fernando Irarrázaval's AI agent experiment drew over 6,000 hack attempts from more than 2,000 attackers. No one could break it.

Developer Fernando Irarrázaval's AI agent experiment drew over 6,000 hack attempts from more than 2,000 attackers. No one could break it.

OpenClaw's Fiu AI blocked over 6,000 prompt injection attempts from 2,000 attackers in a public test, but the platform's 2026 security record tells a more