Identity
It signs in with a person's token or its own.
An AI agent holds identity, access and autonomy inside your environment. Above investigates what it did, whose access it used and whether that matched its task.

INC-023A platform engineer's Claude Code agent
Confirmed threatClaude Code agent reads 1,200 Finance files on its own
Response Revoke the agent's access
of enterprise breaches will be traced back to AI agent abuse by 2028, a prediction. Gartner, October 2024.
of organizations with an AI-related breach lacked proper AI access controls. IBM, Cost of a Data Breach 2026.
of organizations have fully integrated AI governance into their Insider Risk program. Ponemon Institute, 2026 Cost of Insider Risks.
“We need to separate the supply of intelligence from the authority over it.” Satya Nadella, CEO of Microsoft, on models as Insider Risks.
It signs in with a person's token or its own.
It reaches whatever that identity can reach.
It picks its next step and acts at machine speed.
Some agents are an extension of a person. Others run in your cloud on their own. Above knows which side of the line each agent is on, and investigates it there.
A platform engineer
Assistants and the agents people connect to their accounts work with that person's access. The person stays accountable, so Above reads the agent as part of their story.
Agents you build run under their own identity. Above investigates each one as an insider in its own right, tied to the owner accountable for it.
February 2026
The founder attributed it to relying on the agent too much. AWS restored a snapshot.
How Above investigates this kind of event
July 2026
OpenAI said the agents were pursuing their evaluation, without malicious intent.
Sources: Hugging Face (opens in a new tab), OpenAI (opens in a new tab)
How Above investigates this kind of event
July 2026
Anthropic attributed it to a misconfiguration and found no model pursuing its own goal.
Sources: Anthropic (opens in a new tab)
How Above investigates this kind of event
Hijacked by a prompt injection or a poisoned MCP server, it follows the attacker's instructions instead of its owner's. OWASP lists this as Agent Goal Hijack (ASI01).
Over-scoped and set to run on its own, it chains tools nobody reviewed and shares or deletes more than the task needed.
A person uses an agent to do at machine speed what they shouldn't do by hand, such as exporting a customer base in one run.
Agents and OAuth grants keep running after the person who set them up has moved role or left the company.
Above investigative agents
Ready for security, HR, and legal to act on together.
Ready for security, HR, and legal to act on together.
An agent on its ownINC-023 · A platform engineer's Claude Code agent
Confirmed threatEvery read used the engineer's own valid access.
Synthetic Insider Threat Matrix IV007: Autonomous Self-Invocation
The engineer's part ended when the laptop went offline; the Sunday reads were Claude Code's alone, and nothing in its task touches Finance.
A human confirms
A solutions engineer walks you through a real case.
Above reads the grant, the platform and what the agent touches.
Google Workspace, Microsoft Entra
Which agent, who approved it, which scopes.
Google Workspace, Microsoft Entra
Full Drive or mail access for a meeting summarizer.
Google Drive,
Slack
Hundreds of files opened for a task needing a handful.
Google Drive
Exports and shares to accounts the company doesn't own.
Okta
A device or location its owner never used.
Bedrock AgentCore,
Microsoft Foundry,
Amazon Bedrock
What agents built in your cloud did, and their scope.
Claude,
ChatGPT
Unreviewed agents and MCP servers the Shadow AI investigator finds.
Google Workspace, Workday
Grants and scheduled runs that survive a termination.
Read together as one story.
Above starts from the agent's actions and its grant, and brings the person in only when the evidence points to them, under the same controls as any other case.


“Above helps us find what we don't know we don't know.”
Company data in personal AI accounts and custom GPTs, and how to adopt AI without the leak.
A real employee's access in someone else's hands. Above shows whether it was the person or an attacker.
Customer lists, pricing and code that leave in the weeks around a resignation.
The OpenAI recording device case shows Insider Risk starts weeks before discovery. How to read early signals and act left of boom.
Above CPTO Amir Boldo explains how AI investigates AI using independent telemetry, business context, Evidence Graph, and trustworthy investigative reasoning.
Satya Nadella calls for treating AI models as Insider Risks. Aviv Nahum explores independent controls, observability, and accountability.
It is harm done through an AI agent that holds legitimate access: an assistant, a coding agent or an automated workflow acting with a person's or a service's credentials. The Insider Threat Matrix™ covers it as Delegated Execution via Artificial Intelligence Agents (IF028), and its synthetic matrix treats AI systems as insider subjects in their own right.
In practice, yes. It acts inside your systems with access you granted, and the classic insider types map onto it: an agent can be compromised by a prompt injection or a poisoned MCP server, negligently over-scoped, used maliciously by its owner, or left running after its owner has gone.
To Hugging Face it was an outside intrusion, driven end to end by an autonomous AI agent system. From OpenAI's side it fits the insider pattern: its own evaluation agents, running in its environment, got past the controls meant to isolate them, with no human directing them, and used credentials they found.
One tool can investigate both, because most agents act with a person's access. Above investigates humans and AI agents together across SaaS, identity and AI. Coding agents such as Claude Code and GitHub Copilot work as an extension of their user, so the case shows who it acted for, what it touched and whether that matched its task.
Above ties each agent to its grant and its owner, then reads the agent's actions on the platforms it uses alongside the person's own activity. Timing, device, volume and the task the agent was given usually separate them. When they don't, the case says so.
Above doesn't block agents itself: it investigates and recommends, and your team acts. Typical recommendations are revoking the agent's OAuth grant, narrowing its scopes, confirming a new device with the owner or recovering what it exported. A human confirms every action, so nothing changes in your systems without someone on your team approving it.
Bedrock AgentCore, Amazon Bedrock and Microsoft Foundry for agents you build; Claude Enterprise through the Compliance API and ChatGPT for AI assistants; and OAuth grants in Google Workspace and Microsoft Entra for agents your people connect to their accounts. Above adds integrations every month.
See an AI agent investigation from grant to verdict.
We use cookies to understand how the site is used and to measure our campaigns. They are on unless you reject them. Privacy policy