تغريدة مثبتة

AI Pentesting Just Got a Major Upgrade
Argus Benchmark (60 defense-enabled Dockerized web apps):
All Challenges (Haiku 4.5)
• Apex (Pensar AI) → 35% success rate 🏆
• PentestGPT → 30%
• RAPTOR → 27%
Top 10 Hardest Challenges (Opus 4.6)
• Apex → 80%
• PentestGPT → 70%
• RAPTOR → 60%
New open-source autonomous agent that spawns swarms of sub-agents, shares memory, and chains complex exploits. Battle-tested in production at financial institutions and startups.
The future of red teaming is here.
Kerem Proulx ⌘@ProulxKerem
Our autonomous pentesting agent just outperformed the two most popular open source offensive security agents on a benchmark of 60 modern, defense-enabled web apps. Battle-tested in production against our customers' environments from startups to financial institutions, Apex consistently finds and exploits critical vulnerabilities other agents and humans miss. Today we're releasing it open source alongside our internal benchmarks.
English






