置顶推文
🚨 A deeper shift is emerging in cybersecurity.
Pensar’s Apex uses coordinated subagents with shared memory to map attack surfaces and chain multi-step exploits, moving closer to human-like red teaming at scale.
With both the agent and its “Argus” benchmark now open sourced, this could accelerate innovation in AI-driven offensive security and redefine how systems are tested.
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
