Skip to content
AI Pentesting Benchmarks Are So Bad, We Made a New One
ethiack.com | research | #ai-security | #pentesting | #benchmark | #vulnerability-discovery | #ethibench
Summary
Ethiack built EthiBench to score AI pentesting agents on validated vulnerability discovery, not CTF flags, spanning 108 expert-annotated flaws across three open-source targets.
- Published
- Collected