Fabraix automates red teaming, exploits bank agent with invoice image

aftahi_ai · x · 2026-08-20

FabraixHQ launched an automated continuous red teaming tool to bridge the trust gap in AI agents. The black-box solution requires no wiring and reduces senior engineer testing time from weeks to hours. It achieved a 78% attack success rate on the AgentHarm benchmark and successfully exfiltrated a bank customer's balance using a normal-looking invoice image, identifying exploits before real attackers do.

Related event: Fabraix Unveils Automated Red-Teaming Tool That Breaks AI Agents with an Invoice(2 posts)→

Original post →

More from Safety

Safety channel →