Siddarth Surana
Teleport back

Ironhide

Penetration testing for AI agents.

Role
Founder
Status
Currently building — stealth
Year
2026
Live
ironhideai.com

The problem

AI agents don't just answer questions any more. They take actions, call tools, move through environments, and hold real permissions. The blast radius of a mistake is no longer a bad paragraph — it's a write to a production system.

Application security tooling was built for software whose control flow you can read. It doesn't model an agent that decides what to do next at runtime, so the interesting failures — the ones that come from the agent reasoning its way into something it shouldn't do — go unexamined until they happen in production.

What I built

Ironhide is a security layer built specifically for agent behavior: test an agent against the environment it will actually operate in, find the exploitable paths, and verify before deployment rather than after an incident.

It lives in the developer workflow rather than beside it — connect an agent, point it at a target environment, and get a verdict as part of shipping, the same way you'd run a test suite.

Selected details

Where it sits

A CLI-first workflow that fits into existing source control and deployment pipelines, so verification happens on the path to production instead of in a separate security review.

What it tests

The agent as it behaves in its target environment — tools, permissions, and the paths it can reason its way down — rather than generic application scanning against a static surface.

Where it landed

In active development. Details are deliberately thin here while the company is in stealth.