AI-powered fuzzing with the GitHub Security Lab Taskflow Agent

Selection record

AdmittedSum of both 124 ≥ twice the threshold 120

Source tier

Official, first-hand; this tier's threshold is 60

Pre-filter

passed：GitHub Security Lab的LLM Agent驱动模糊测试流水线

Why it was chosen

The article fully describes the architecture's responsibilities and coverage feedback loop, showing practical boundaries for LLM agents in security automation.

A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.