GitHub Security Lab open-sources an AI fuzzing pipeline that writes and tunes its own harnesses

GitHub Blog AI/ML · rss · 2026-09-25

GitHub Security Lab's Fuzzing Taskflow is an autonomous fuzzing pipeline for C/C++ repos: point it at a GitHub project and an LLM agent installs AFL++, identifies entry points, writes harnesses, runs coverage-driven improvement loops, triages crashes, and writes vulnerability reports. Built on the Taskflow Agent framework with MCP tools, it defaults to Claude Sonnet 5 and ships structure-aware mutators for JSON, XML, regex, PNG and TLV. The authors warn it executes arbitrary build commands on the host, so run it only in disposable environments.

Original post →

More from coding & agent

coding & agent channel →