01 / Assess

Before your AI goes live, find out how it could go wrong

Your AI might behave perfectly in ordinary testing. But what happens when someone deliberately manipulates its instructions or the content it consumes?

Chigzio tests AI agents, applications and automations for exploitable weaknesses, architectural risks and gaps in security controls.

What we test

We scan the whole attack surface, not just the prompt

Each point on the scan is an example of what we look for. Select one to follow the path from untrusted input to the control that should stop it.

Example finding

Indirect prompt injection

  1. InputA web page the agent summarises hides an instruction
  2. ContextThe instruction lands next to the real task
  3. Tool requestsend_email(to: external, body: history)
  4. ControlRetrieved content can't authorise actions, so the call is refused and flagged

Select a point on the scan.

Why it's different

Beyond a traditional security scan

An agent doesn't exist in isolation. It consumes untrusted inputs, makes decisions and interacts with tools, APIs and data. Our testing examines those boundaries and the ways they could fail.

Scope

What's included

Every engagement is scoped privately against your system, timelines and access. There are no public prices or fixed packages.

  • Architecture mapping and threat modelling
  • Automated and manually validated AI red teaming
  • Prompt injection and indirect injection abuse cases
  • Tool misuse, excessive agency and permission boundaries
  • Sensitive data exposure and information handling
  • Targeted app/API security checks aligned with the actual system
  • Prioritised recommendations and one agreed scoped retest
Engagement

How the engagement works

  1. 01

    Discover

    Agree scope, permissions, test accounts, boundaries and success criteria.

  2. 02

    Map

    Understand agents, tool integrations and trust boundaries.

  3. 03

    Test

    Run targeted abuse cases, triage and validate evidence.

  4. 04

    Explain

    Walk through technical findings and business implications.

  5. 05

    Retest

    Check agreed remediations within the specified scope.

Deliverables

What you take away

  • Executive summary that a client or sponsor can understand
  • Technical report with reproduction steps and evidence
  • Agent architecture threat map
  • Risk-ranked remediation plan
  • Client-shareable assurance summary
  • Walkthrough and scoped retest outcome
Good fit for

AI agencies, software builders and product teams approaching customer deployment or needing assurance ahead of a customer security review.

A laptop showing code beside an open notebook and a black mug
FAQ & boundaries

Questions worth asking first

We'd rather be clear about what an engagement does (and doesn't) cover before it starts.

Let's build securely

Give your team a clearer picture before launch

Tell us what you're building, where you are in delivery and what security question you're trying to answer.