xbow

Autonomous multi-agent pentest framework — plans, exploits, verifies (proof-required), CVSS-scores and writes client-ready reports. 104/104 (100%) on the XBOW validation benchmarks, powered by Kimi K3.

A reproducible study of LLM penetration-testing agents measuring how model backbone, agent scaffold, backend substrate, and scoring integrity affect exploit success.

An interactive analytics dashboard designed to visualize the difficulty distribution, vulnerability coverage, and structural diversity of the Xbow benchmark suite.

Xbow matchup guides.

Fully autonomous AI hacker to find actual exploits in your web apps. Shannon has achieved a 96.15% success rate on the hint-free, source-aware XBOW Benchmark.

A High-Efficiency Penetration-Testing Agent

The Ninja Tables plugin for WordPress (versions < 4.1.9) contains a critical vulnerability in the AJAX action ninja_table_force_download.