kin

코드를 위한 새로운 기반. Kin은 사람과 AI 에이전트를 위한 그래프 네이티브 코드 저장소입니다. 소스, 기록된 코드 관계, 버전 관리된 이력을 저장소 상태로 저장합니다. 그래프는 저장소 모델이며, 다른 저장소 옆에 유지되는 검색 인덱스가 아닙니다. 함수, 타입, 그리고 그들 사이의 관계는 커밋하고, 브랜치하고, 병합하는 데이터입니다. 정확한 소스는 바이트 단위로 보존되며, 파일시스템 프로젝션을 통해 지원되는 도구들이 일반 파일로 계속 작동할 수 있습니다. 퍼블릭 베타. 잘 알고 있는 실제 프로젝트에서 Kin을 사용해 보세요...

demo-cve-2026-4821

デモ：CVE-2026-4821 脆弱性修復 本リポジトリは、OpenExecutionのプロベナンスシステムがAIエージェントのCVE修復を完全な暗号学的監査可能性で追跡する様子を実演します。 シナリオ 脆弱性 ：認証モジュールのSQLインジェクション エージェント ：sentinel-x9 CyberSafe Inc. フロー ：検出 → AI分析 → 人間の指示 → 修正 → レビュー → 証明書 プロベナンス provenance/ 内の全アーティファクトは暗号署名済みで、独立検証可能です。 node provenance/verify.js を実行して検証してください。...

Agent-Warden: EBPF-Based Kernel-Native Process-File Provenance Tracking for LLM Agents

LLM agents execute dynamically generated process and file operations that are often invisible to application-layer tracing. We present Agent-Warden, an extended Berkeley Packet Filter eBPF-based provenance monitor for tracking task and regular-file states across process creation, file access, and...

Topological Attribution Distance (TAD): Revealing Segment-Level RAG Influence on LLM Output Geometry for Incident Log Analysis

Large Language Models LLMs are increasingly being deployed in cybersecurity operations to assist cybersecurity analysts with rapid decision-making against emerging threats. However, there is a main criteria that must be met when using LLMs in cybersecurity, that is, trust in the generated outputs...

kin v0.4.8

The diff is not the change. AI agents can write a change faster than a team can establish what it touches, whether it reverses an earlier fix, and how far its consequences reach. Git records files and line history. Kin records the software itself as a graph of entities, relations, changes, and...

MutMem: Cryptographically Authorized Mutation in Persistent Agent Memory

Persistent agent memory must adapt as later outcomes change earlier evidence, yet mutable retrieval weights create an attribution problem: reviewers must distinguish authorized adaptation from database tampering. We present MutMem, an authorized-mutation protocol in HOM-AIMOS, a persistent...

REFORGE: A Method for Benchmarking LLMs' Reverse Engineering Capabilities in Decompiled Binary Function Naming

Large language models LLMs are increasingly applied to reverse-engineering tasks, and recent threat-intelligence reporting shows them operating inside live offensive-security workflows. Claims about their capability, however, outpace our ability to measure it. Existing benchmarks for LLM-assisted...

Silent Subversion: Sensor Spoofing Attacks Via Supply Chain Implants in Satellite Systems

Spoofing attacks are among the most destructive cyber threats to terrestrial systems, and they become even more dangerous in space, where satellites cannot be easily serviced, and operators depend on accurate telemetry to ensure mission success. When telemetry is compromised, entire spaceborne...

Toxic_Flow_Analysis_Framework_For_Agentic_AI

Toxic Flow Analysis TFA Framework A Secure-by-Design framew...

Securing the Model Context Protocol (MCP): Risks, Controls, and Governance

The Model Context Protocol MCP replaces static, developer-controlled API integrations with more dynamic, user-driven agent systems, which also introduces new security risks. As MCP adoption grows across community servers and major platforms, organizations encounter threats that existing AI...