Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents

Abstract

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)

Categories

Framework mappings

Suggested from the entry's categories.

@misc{eliav2026know,
  title = {{Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents}},
  author = {Or Zion Eliav and Eyal Lenga and Shir Bernstien and Yisroel Mirsky},
  year = {2026},
  month = jul,
  eprint = {2607.19837},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.19837}
}