LATIDIA · Ciberseguridad

Thinking in Graphs: Neo4j-Backed Exploit-Chain Reasoning for LLM Penetration-Testing Agents

arXiv:2610.20902v1 Tipo de anuncio: nuevo Resumen: los agentes de codificación LLM como Claude Code y OpenAI Codex pueden impulsar herramientas de prueba de penetración, pero razonan sobre un compromiso como una lista plana de hallazgos en un contexto

La noticia

arXiv:2610.20902v1 Announce Type: new Abstract: LLM coding agents such as Claude Code and OpenAI Codex can drive penetration-testing tools, but they reason about an engagement as a flat list of findings in a context window. Attackers think in graphs: isolated low-severity exposures turn catastrophic once chained through credential capture, privilege escalation, and lateral movement. This gap feeds a common belief that AI agents cannot truly chain exploitation; we argue this describes the flat context window, not the model. We present ChainGraph, a pattern that externalizes exploit-chain reasoning into a Neo4j property graph wired to an off-the-shelf agent via the Model Context Protocol, no bespoke harness. Findings, attack steps, credentials, assets,