samugit83

RedAmon is an open-source, self-hosted AI penetration testing framework. It maps your attack surface into a Neo4j graph, then autonomously exploits it from a Kali sandbox with human approval gates . GitHub: samugit83/redamon #RedAmon #AIPentesting #Cybersecurity #OpenSource #InfoSec

오픈 소스 자체 호스팅 AI 침투 테스트 프레임워크 redamon 공격 표면을 그래프로 매핑하고, 사람의 승인 절차를 거쳐 Kali 샌드박스에서 자율적으로 취약점을 공격하며, 발견된 문제점을 수정하는 PR을 생성합니다. 양방향 MCP도 지원 많은 기능들이 포함되어 있네요!!~ samugit83/redamon

Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules Samuele Giampieri arxiv.org [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸] 💬Code: samugit83/cortex t.co

Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules Coding agents such as Claude Code also follow text files that developers write for them: a project file, skills the agent may choose to open, and rules that load automatically when the agent reads matching files. We call these files the agent's harness. Developers add to it whenever they correct the agent, but one success proves little: the same agent can pass a task once and fail it the next time. We present Cortex, a tool that tests changes to the harness instead of trusting them. It saves fixes from the developer's sessions as replayable tasks, finds the corrections that recur, writes one skill or rule at a time, and keeps it only if repeated runs with and without it show a net gain and no task made noticeably worse. Existing text is tested the same way before it is deleted, and Cortex neither adds nor deletes text the agent never used. We tested Cortex with Claude Haiku 4.5 on a repository built for the purpose, with conventions the model tends to break, one area with nothing to learn, and a script playing the developer. On held-out tasks, the harnesses it built made the agent follow the conventions far more often than no skills or rules did, left the comparison area unchanged, and added no text read on every turn. Rules, which load automatically, did most of the work; skills helped only when offered with the files a task touches, and those offered on every turn were rarely opened. Cortex kept none of the useless or harmful suggestions we planted, but the agent never opened the useless ones or the harmful skills, and it reached no verdict on the harmful rules, so the test shows that Cortex keeps no unused text, not that it detects damage. Under the stronger Claude Sonnet 5 a single run's harness added little, and on a real open-source project, where the agent was rarely corrected, Cortex found nothing to learn. We release the tool, the lab and its data. Comments: 46 pages, 22 figures, 8 tables. Abstract abridged. Code and data: samugit83/cortex

・RedAmon samugit83/redamon 攻撃面をグラフ化して、Kaliサンドボックス上で自律エクスプロイト。人間承認ゲート付きで、見つけた脆弱性の修正PRまで作ろうとするタイプ。