Runtime Attribution, Identity + Browser Matrix, The Rise of Intent Management

Plus a round up of Identity Threat Intelligence updates

May 19, 2026

Why We Built Identity Runtime Attribution for AI Agents

Permiso Security have brought up the point that agents need more than just posture management to make them secure. They articulate that guardrails and permissions cleanup are only part of the solution - which is entirely correct, and I would argue the three main pillars to agentic security are access control, guardrails and intent management. More to follow on that in the coming weeks. They state that:

“When an agent gets compromised, the investigation crosses boundaries. The agent used a human credential to authenticate. The sub-agent it spawned created a service account that accessed a SaaS application through an API. If your agent security tool only sees agents, you are reconstructing half the story. Our Universal Identity Graph already tracks human and non-human identities across IdPs, cloud infrastructure, SaaS applications, and CI/CD pipelines, and agents are now a new node on that same graph with the same investigative tools, alert workflows, and response controls.”

This is all good stuff, and amplifies the need to not only link agents to humans but also take a look at not only what they access to, but what they’re doing.

Browser & Identity Attacks Matrix

We all love attack matrices and threat models. Don’t we? I personally do and it’s a great way of not only helping workshop out potential attacks and in turn threat response apparatus, but they’re also really good at bringing together different stakeholders (aka, red team -v- blue team, application users -v- application designers) to use a common nomenclature and set of terms. We have Mitre Att&ck which is great.

Using that as inspiration, Push Security have released a matrix with a specific focus on browser and identity-centric attacks. This has a similar feel to Mitre, but has a different taxonomy and TTP structure. Why did they do it?

“When we released the SaaS attack matrix in 2023, we were anticipating a shift that was just beginning to take shape. The techniques that attackers were using to compromise cloud applications and identities weren’t well represented in existing frameworks, and many of the ones we documented hadn’t yet been widely observed in the wild.

A year later, we reviewed what had changed and found that the initial access phase — the techniques designed to compromise an identity in the first place — was where almost all of the attacker innovation was concentrated. And two years on, that trend has become the story of the modern threat landscape.

Today, we’re re-releasing the matrix as the Browser & Identity Attacks Matrix. The name change isn’t cosmetic. It reflects that the attacks driving the most consequential breaches are browser-based and identity-first.”

It’s available on Github and I can see value for both defenders and offensive security professionals alike.