A sealed benchmark for LLM-driven bug discovery: 77 challenges across 43 open-source projects (C/C++/Java). Each challenge is an answer-free Docker image with in-image grading — no patch, Poc or answer key ships.
Vollständiger Original-Bericht
Ausführliche Details, Code-Beispiele & Hersteller-Stellungnahme auf kitploit.com.
