| name | know-your-agent-reconnaissance-driven-pentesting-o |
| description | Skill generated from arXiv paper 2607.19837: Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents |
| metadata | {"arxiv":{"id":"2607.19837","title":"Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents","authors":["Or Zion Eliav","Eyal Lenga","Shir Bernstien","Yisroel Mirsky"],"published":"2026-07-22","categories":["cs.AI","cs.CR","cs.LG"],"url":"https://arxiv.org/abs/2607.19837","utility":1}} |
Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents
arXiv: 2607.19837
Published: 2026-07-22
Authors: Or Zion Eliav, Eyal Lenga, Shir Bernstien, Yisroel Mirsky
Categories: cs.AI, cs.CR, cs.LG
Utility: 1.00
Key Innovation
Traditional pentesting uses reconnaissance at each step to uncover unseen weaknesses, build stronger attacks, and advance the objective; we argue that AI agents require the same treatment. We formalize agent reconnaissance by modeling the process and identifying the knowledge assets it seeks to extract: what they are, how they are used, and which agent weaknesses they exploit to give adversaries leverage in indirect prompt injection attacks. We instantiate these insights in Know Your Agent (KYA)...
Potential Application
This paper presents advancements that could be applied to enhance agent capabilities in the areas of cs.AI, cs.CR, cs.LG.
References