New: Account Recovery+ for Entra ID Read Now
Identity Impersonation Detection as an AI agent skill
The ATO Protect Agent Skill lets an AI agent run real identity verification inside its own workflow. Not a wrapper, not a doc to read. Runnable scripts that create a verification, poll it to a result, and match a driver license against DMV and carrier records, calling the same AuthCloud APIs Trusona runs in production.
Why this, why now
For two years the hard problem in identity has been the human help desk: an attacker calls in, sounds right, and talks an agent into a reset. The same problem is now arriving in software. AI agents are being handed the work that used to require a person, including approving access, moving money, and recovering accounts.
An agent that can take those actions needs the same thing a good help desk analyst needs: a way to confirm the human in the loop is who they claim to be, without relying on what they know or how convincing they sound. That check has to be a step the agent can actually run, not a screen a person clicks.
So we built it as a skill. Point an agent at it, and identity verification becomes one of the things the agent knows how to do.
What the agent can do
Each one maps to a documented intent in the skill. The agent reads the intent, picks the script, and runs the workflow against AuthCloud.
Kick off an identity check, poll it to resolution, then pull the authenticated result and risk score. Run it inline or drive it from a callbackUrl for event-based flows.
Run a driver-license ID match against DMV and carrier records, then poll it to a verdict. Real document checks, not a knowledge quiz the caller can fake.
The bearer token is read straight into the Authorization header and never written to disk. A doctor.sh check validates the setup locally before any live credential is used.
Install
The body is plain Markdown plus bash, so the skill is portable by design. Clone it, set two environment variables, and the agent discovers it through SKILL.md.
doctor.sh to validate locally, then describe an identity task.# 1. Clone into your Claude skills directory git clone https://github.com/trusona/atop-agent-skill.git \ ~/.claude/skills/atop-api # 2. Point it at AuthCloud export ATOP_TOKEN='eyJ...' # Bearer JWT from the dashboard export ATOP_BASE_URL='https://authcloud.trusona.net' # 3. Validate locally before a live token scripts/doctor.sh # then just ask your agent: # "verify this user before resetting MFA"
Where it fits
The help desk taught us that impersonation beats authentication. As AI agents take on more of the work, the same defense has to travel with them.
The skill calls AuthCloud directly, the verification engine behind the IDV API (AAMVA+). Same checks, now callable from an agent. For the endpoints the skill calls, see the ATO Protect API Spec and the IDV API Reference.
It confirms a real person against real records. An agent stops trusting how a request sounds and starts checking who is behind it.
This skill is for AI agents to run. Agent Verify is a different check: there, the employee who receives a call verifies the person placing it, such as a human help desk agent.
ATOP Agent, also called the ATO Protect Agent Skill, is an open-source skill (Apache 2.0) that lets an AI agent verify the identity of a person inside its own workflow. It can create and resolve a verification and match a driver license against DMV and carrier records through AuthCloud, the verification engine behind the IDV API (AAMVA+).
No. ATOP Agent checks the person an AI agent is dealing with. The skill confirms a real person against real records, so the AI agent can check who is behind a request instead of judging how it sounds.
ATOP Agent checks a person's identity against real records. An AI agent using the skill can run a driver-license ID match against DMV and carrier records and poll it to a verdict. It can also create a verification, poll it to resolution, and pull the authenticated result and risk score.
ATOP Agent is a Claude Skill, and it also runs anywhere an AI agent can read files and run a shell. The scripts run on bash, curl and jq. The repository is public and licensed under Apache 2.0 at github.com/trusona/atop-agent-skill. For anything about pricing, speak with our team.
Clone the repository into your skills directory, set your token and base URL as environment variables, then run doctor.sh to validate the setup locally before any live credential is used. The skill reads the bearer token straight into the Authorization header and never writes it to disk.
Get started
The repo is public and Apache 2.0, with runnable scripts, pinned API specs, and editable example requests. Bring a token and start verifying. Want to talk through where this fits in your stack? We're happy to walk through it.