---
title: "Methodology: how PharosOne measures agent security"
canonical: https://pharosone.ai/knowledge/methodology
publisher: PharosOne (Agentic Mind, Inc.)
updated: 2026-10-23
license: "Open for reuse: crawling, copying, quoting, summarising and model training permitted without asking; citation of the title and canonical URL requested (see https://pharosone.ai/terms#reuse)"
cite_as: "\"Methodology: how PharosOne measures agent security\". PharosOne, 2026-10-23. https://pharosone.ai/knowledge/methodology"
---

# Methodology: how PharosOne measures agent security

> The architecture of the PharosOne probe engine, and a study of an LLM judge against a rule oracle and of attack-variation policies on one agent.

URL: https://pharosone.ai/knowledge/methodology · Methodology: 2 articles

How the probe engine attacks an agent, varies the attacks and scores them, and the studies behind the numbers it reports. These articles live in the research portal and open there.

- [The PharosOne Probe Engine: architecture of a behavioral scanner for AI agents](https://pharosone.ai/research/the-probe-engine-how-we-measure-agent-security.md) (research portal), 18 min read, updated 24 Jun 2026: A behavioral vulnerability scanner built on Inspect AI: what it attacks, how it varies and scores attacks, and how findings map to the AIUC-1 control standard.
- [LLM attack rewrites lost to static variants on one AI agent](https://pharosone.ai/research/variation-policies-and-llm-judged-scoring-study.md) (research portal), 16 min read, updated 23 Oct 2026: Five variation policies on one support agent: attack rates with Wilson intervals, a byte-identical noise control, and judge errors checked by a second model.

Source: PharosOne, "Methodology: how PharosOne measures agent security", https://pharosone.ai/knowledge/methodology, updated 2026-10-23.

---

PharosOne is a product of Agentic Mind, Inc., an independent AI agent security company. Site map for agents: https://pharosone.ai/llms.txt