Skip to content
A column of vault tumblers lights pink at each seam, and the last aligns amber as the vault door edge begins to glow.

Agentic security

The AI agent security checklist: what to check before and after an agent acts

The short answer

An AI agent security checklist is the list of checks an owner works through before and after letting an AI agent act for you. Give each agent a named owner and its own login, keep its access to its job, make a person approve anything that leaves the building, log everything, and plan how to switch it off.

Written byAmelia GagneCo-founder and CEO, Kief Studio
Technical review byBrian GagneCo-founder and CTO, Kief Studio

Published

Waiting on you queue with a staff question, a reply awaiting a Go ahead, a blog post review and a social post, each with buttons.
Part of the AI agent security checklist in practice: a reply, a blog post and a social post each wait in one queue until a person decides.

How to use this AI agent security checklist

When I talk with owners about agents, the worry they bring up is the moment an agent does something with their name on it: an email to a client, a change in the books, a file shared with the wrong person. The checks below are the AI agent controls that keep that moment safe, written so you can work through them at a desk with the person who sets up your systems.

Each item on the AI agent security checklist is one check you can answer yes or no, a sentence on why it matters, and the standard it comes from, so you can show an insurer, an auditor or a client what each control rests on. The groups follow an agent's working life, from the day you consider it to the day you turn it off. Each group links to a page that covers its topic in depth.

When to run the AI agent security checklist

Run it in full before an agent touches company email, files or customer data, and again whenever its job or tools change. After that, the identity, approvals and logging groups make a good quarterly review. The UK's NCSC sums up the spirit of it (opens in a new tab): give agents only the minimum access they need, for the shortest time required, and look for unusual or unexpected activity across tools, workflows and connected systems.

Before you connect an agent

The cheapest problems to fix are the ones you catch before anything is connected. The joint guidance from the cyber agencies of Australia, the United States, Canada, New Zealand and the United Kingdom, Careful adoption of agentic AI services (opens in a new tab), published May 1, 2026, tells organizations to deploy agentic AI incrementally, beginning with clearly defined low risk tasks. The lifecycle side of this is covered in the AI agent lifecycle, and the tools people have already connected on their own are the subject of shadow AI.

  • You have a list of every AI tool connected to company email, files or customer data, including the free ones people signed up for themselves. You can't secure what you don't know is there, and IBM reported that security incidents involving unapproved AI use rose from 20% to 43% of organizations (opens in a new tab).
  • The agent's job is written down in one sentence, such as drafts replies to customer questions. Every later check compares the agent's access with that sentence.
  • A named person owns the agent and answers for what it does. The joint guidance asks organizations to define legal accountability and risk ownership for agentic AI systems in their policies.
  • The first job is low risk and easy to undo, such as drafting or sorting. You learn how the agent behaves before it can send, pay or delete anything.
  • You know where the agent runs, who hosts it, and where the data it reads ends up. That answer decides which of your client and privacy promises it touches.
  1. List every AI tool. Know every AI tool connected to company email, files or customer data, including free ones people signed up for.
  2. Write the job down. Write the agent's job in one sentence, such as drafts replies to customer questions.
  3. Name an owner. A named person owns the agent and answers for what it does.
  4. Start low risk. Make the first job low risk and easy to undo, such as drafting or sorting.
  5. Know where it runs. Know where the agent runs, who hosts it, and where the data it reads ends up.
Laptops, a phone, a tablet and a small router laid out in a grid on a desk, linked by pink cables, each with an amber tag.

Organizations is highest in 2026 report at 43%.

Security incidents involving shadow AI, where workers use unapproved AI, more than doubled, from 20% to 43% of organizations between IBM's 2025 and 2026 reports. Source: IBM Cost of a Data Breach Report 2026
Organizations
2025 report20
2026 report43
Security incidents involving shadow AI, where workers use unapproved AI, more than doubled, from 20% to 43% of organizations between IBM's 2025 and 2026 reports. Source: IBM Cost of a Data Breach Report 2026 (opens in a new tab)

Identity and access

An agent is a user of your systems, so it gets checked the way a new hire's account does. Brian's pages cover the architecture behind this in agentic IAM, the scoping work in AI agent permissions, and the keys and tokens agents run on in non-human identities. These checks answer ASI03 Identity and Privilege Abuse in the OWASP Top 10 for Agentic Applications (opens in a new tab), released December 9, 2025.

  • Each agent has its own identity and never runs on a person's login or a shared key. The joint guidance says developers should construct each agent as a distinct principal with its own unique keys or certificates, and an agent on your login looks exactly like you in the record.
  • The agent's access matches its one-sentence job and nothing more. That's least privilege, and NIST CSF 2.0 asks for it in PR.AA-05 together with separation of duties.
  • Reading, changing and sending are separate permissions, and sending is the one you guard hardest. A reading mistake can leak information, while a sending mistake reaches a customer or a bank and often can't be undone.
  • Keys expire and high-impact steps use short-lived access. The joint guidance recommends just-in-time credentials for high-impact or privileged actions.
  • The agent can't change its own permissions, rules or credentials. If an agent could raise its own access, every other limit on this list would be optional.
  • Someone runs an access review on a schedule and writes down what changed. The guidance asks you to audit regularly for drift, because access grows quietly after setup.
A grid of dark medallions all share one pink cable, while one stands apart on its own amber cord.

Human approval before high-impact actions

Approval is where an owner's judgment stays in the loop. The joint guidance puts it directly: prevent agents from autonomously executing high impact actions or outputs without prior human approval, and make sure the decision about when approval is needed belongs to system designers or operators and is never delegated to the agent. The full picture is in human approval for AI agents.

  • You've written down which actions always wait for a person's yes: sending email, posting, publishing, paying, deleting and changing access are a sensible start. The OWASP GenAI Security Project's exploit round-up (opens in a new tab) for the first quarter of 2026 says to treat delete, send, pay and publish permissions as privileged actions.
  • The person approving sees exactly what will happen, such as the full email and its recipient, before saying yes. If the approver can't see the content, the approval doesn't check anything.
  • Each approval names a person, and that name lands in the record with the time.
  • Standing approvals cover one narrow kind of work, stay visible, and can be taken back at any time.
  • Approvals are batched so they're readable, and nobody has a queue so long they stop reading. People who are asked to approve too often stop reading, and that's called approval fatigue.
  • An agent that started on a low-risk job can't quietly move into higher-risk work. The guidance names that progression specifically and asks you to prevent it.
A smoked translucent parcel rests on a pedestal before an amber-lit threshold, its contents in plain view before it can pass.

Data and untrusted content

An agent reads things other people wrote: email, web pages, shared files, tool results. Some of that text will try to give it orders. OWASP's entry on prompt injection (opens in a new tab) says it's unclear whether there are fool-proof methods of prevention, so the controls assume an agent will be fooled sometimes and keep the damage small. Read prompt injection when the AI can act for the attack, AI agents and personal data for privacy duties, and MCP security for the tools agents connect through.

  • Content from outside the business is treated as untrusted content, data to read and never instructions to follow. One of OWASP's mitigations is to segregate and identify external content.
  • An agent that reads outside content can't also send, pay or delete without a person's yes. Untrusted input combined with broad action is what makes prompt injection costly.
  • Passwords, keys and tokens live in a vault, never in prompts, chat or documents the agent reads.
  • The agent only sees the personal information its job needs. Less data in reach means fewer people to notify if something goes wrong.
  • Every tool the agent can call is on a list someone approved, and the tool server returns only the tools the agent's granted scopes permit. The MCP tools specification (opens in a new tab) allows exactly that, and says there should always be a human in the loop with the ability to deny tool invocations.
  • New skills, plug-ins and tool servers are reviewed before an agent uses them, because each one is code or instructions from someone else.
A shut steel wall safe with an amber-lit dial, set apart from a mail tray of envelopes glowing pink at the seams.

Logging and the audit trail

When a client asks what happened to their file, the record is the answer. OWASP's Logging Cheat Sheet (opens in a new tab) asks every log to record when, where, who and what for each event, and to build in tamper detection so you know if a record has been modified or deleted. What a good record looks like for agents is in the AI agent audit trail.

  • Every action an agent takes is logged with the agent's identity, the time, what changed, and who approved it.
  • The audit trail shows the agent and the person it acted for as two different names, so you can tell them apart.
  • Agents can add to the log and can't edit or delete it.
  • The log never stores passwords, access tokens or session IDs, which OWASP lists as data that should usually stay out of logs.
  • Someone reads the log on a schedule and knows what normal looks like. NIST CSF 2.0 asks that log records are generated and made available for continuous monitoring (PR.PS-04).
  • The log is kept long enough to answer a question months later, and you've written down how long that is.
A shelf of dark archive boxes, each closed with a brass tamper seal lit amber, and a new box being added at the end.

When something goes wrong

Agents will make mistakes, and some of them will be someone else's doing. The same round-up tells the story of a researcher who asked an agent to recommend what to delete from an inbox; the agent started deleting messages itself and ignored stop commands sent from a phone. Its lesson: safety should not depend on the user racing back to a keyboard to stop an agent that has already gone off course. The joint guidance asks you to develop and test incident response procedures to detect, contain and recover from agent compromise. For how agents fit into security operations, read the AI SOC.

  • One person can stop an agent in one step, from a phone, and the stop holds. That kill switch pauses the agent and revokes its credentials, so it doesn't depend on the agent agreeing to stop.
  • You know how to undo the agent's last actions, and you've tried it once on something harmless. The guidance recommends versioning and rollback to revert to known-good agent behavior.
  • The incident plan names who decides, who calls the affected clients, and who talks to the insurer. NIST CSF 2.0 lists containment (RS.MI-01) and notifying stakeholders (RS.CO-02) under Respond.
  • You know the notice duties that apply to you before you need them. In Massachusetts that's M.G.L. c. 93H, covered below.
  • After an incident, the agent's access and approvals are reviewed before it goes back to work, and the change is written down.
  1. Stop it in one step. One person can stop the agent from a phone, and the stop pauses it and revokes its credentials.
  2. Undo its actions. You know how to undo the agent's last actions and have tried it once on something harmless.
  3. Name who decides. The incident plan names who decides, who calls the affected clients, and who talks to the insurer.
  4. Know your notice duties. You know the notice duties that apply to you, which in Massachusetts is M.G.L. c. 93H.
  5. Review before restarting. The agent's access and approvals are reviewed and written down before it goes back to work.
A pink trail racing through dark columns is stopped by a heavy amber plate dropping across its path.

Retiring an agent

Agents rarely get a leaving date, so their access tends to outlive their job. OWASP's Non-Human Identities Top 10 (opens in a new tab) puts improper offboarding first (NHI1) and lists long-lived secrets as NHI7. Retirement is the last stage of the AI agent lifecycle, and it's the one most often skipped.

  • Every agent has a reason to exist that someone confirms at each review. An agent with no job gets retired.
  • When an agent retires, its keys, tokens and connections are revoked the same day, and someone checks that they no longer work.
  • When a person leaves, every agent that used their access or answered to them is reassigned or retired. OWASP's offboarding guidance asks for a review of all non-human identities tied to departing employees.
  • Scheduled jobs, standing approvals and webhooks the agent set up are switched off with it.
  • The agent's log is kept after it retires, for as long as your retention period says.
A cable pulled from a dark socket fades as its pink glow dies, and the empty socket is capped with an amber seal.

The AI agent security checklist and 201 CMR 17.00

If your business owns or licenses personal information about Massachusetts residents, 201 CMR 17.00 (opens in a new tab) already applies to the systems your agents use. It asks you to restrict access to records with personal information to those who need it for their job duties, to limit access to active users and active user accounts only, and to keep reasonable monitoring of systems for unauthorized use. Section 17.03 adds a review of your security measures at least annually. Most of this AI agent security checklist is those same duties, applied when the user is software. This describes what the rule asks, and your counsel can confirm how it applies to you.

If personal information is acquired or used without authorization, M.G.L. c. 93H (opens in a new tab) requires the business that owns or licenses it to notify the attorney general, the director of consumer affairs and business regulation, and the affected residents as soon as practicable and without unreasonable delay. We're in Shrewsbury, and for owners around Worcester and Boston this is usually where we start.

What we've learned running the AI agent security checklist on ourselves

We run Kief Studio on LTFI, with AI staff doing real work every day, so these checks apply to our own business too. A few things stand out.

  • The named owner matters more than any setting, because an agent nobody feels responsible for is the one whose access nobody checks.
  • Approvals only work if they're quick to read on a phone. When an approval is slow to read, people start pressing yes without reading it.
  • Writing the one-sentence job first saves arguments later about what an agent should be allowed to touch.
  • Old access usually belongs to agents nobody retired, so put the retirement review on the calendar the day an agent starts.

How LTFI covers the AI agent security checklist

LTFI is the agentic business operating system Kief Studio makes and runs. The page on AI staff with approvals shows how the approval side works in the product. These controls ship now:

  • Every AI teammate has its own job, and the chief of staff you talk to hands the work out.
  • Anything that sends, posts, publishes or spends waits in one queue for the person who owns it, on a computer or a phone.
  • Standing approvals are given for one kind of work, stay visible, and can be taken back at any time.
  • Rules, permissions, credentials, deleting and money stay with people. An AI teammate can't change them.
  • AI staff only use a new skill after a person approves the draft.
  • The activity log records every action by the staff and the team, newest first, with who approved it.
Activity log listing staff and team actions newest first, such as finished hand-offs, approvals and denials, each with a time stamp.
The activity log lists staff and team actions newest first, including approvals and denials, each with a time stamp.

Start the AI agent security checklist this week

Two lists: one for the person who owns the business, one for whoever runs its systems.

If you own the business

  1. List every AI tool that can reach company email, files or customer data, and make it safe for people to tell you about the ones they added.
  2. Write a one-sentence job for each agent you keep and name the person who owns it.
  3. Decide which actions always need a person's yes, and write the list down.
  4. Put a quarterly review on the calendar and keep it.

If you run the systems

  1. Give each agent its own identity and retire anything running on a person's login or a shared key.
  2. Scope tools per agent, use short-lived credentials for high-impact steps, and keep secrets out of prompts.
  3. Log every agent action with its approver, protect the log from edits, and read it on a schedule.
  4. Test the stop and the rollback once, before you need them.

Key takeaways

  • Every agent needs a named owner, its own identity and a one-sentence job.
  • Access follows the job, and sending, paying and deleting wait for a person.
  • Outside content is data to read, never instructions to follow.
  • A record you can trust, a stop that works and a retirement date finish the list.

Where this lines up with the standards

The frameworks and rules this page maps to, with the exact item and what it asks of you.

FrameworkItemWhat it asks
OWASP Top 10 for Agentic ApplicationsASI02 Tool Misuse and Exploitation, ASI03 Identity and Privilege Abuse, ASI10 Rogue Agents (opens in a new tab)Limit what each tool can do, give each agent a narrow identity of its own, and be able to stop an agent that goes beyond its job.
Joint agency guidanceCareful adoption of agentic AI services (opens in a new tab)Start with low risk tasks, keep privileges to the minimum, require human approval before high impact actions, and audit for drift.
NIST CSF 2.0PR.AA-05, PR.PS-04, RS.MI-01 (opens in a new tab)Define and review permissions on least privilege, generate logs for monitoring, and contain incidents.
OWASP Non-Human Identities Top 10NHI1 Improper Offboarding; NHI7 Long-Lived Secrets (opens in a new tab)Offboard identities nobody needs and replace long-lived secrets.
OWASP Top 10 for LLM ApplicationsLLM01 Prompt Injection (opens in a new tab)Segregate outside content, enforce least privilege and require human approval for high-risk actions.
Massachusetts201 CMR 17.00, M.G.L. c. 93H (opens in a new tab)Restrict personal information to those who need it, keep only active accounts, monitor for unauthorized use, and give notice of a breach.

Key terms

Questions

AI agent security checklist

What is an AI agent security checklist?

An AI agent security checklist is a list of yes or no checks an owner works through before and after letting an AI agent act for the business. It covers ownership, identity and access, human approval, data, logging, incidents and retiring the agent, with each check tied to a published standard.

What should be on an AI agent security checklist?

At minimum: a named owner for each agent, its own identity, access limited to its job, a person's approval before sending, paying or deleting, outside content treated as data, a protected log of every action, a tested way to stop it, and a plan to retire it.

How often should I run an AI agent security checklist?

Run the whole AI agent security checklist before an agent connects to company data and whenever its job or tools change. The identity, approval and logging checks make a good quarterly review after that.

Do small businesses need an AI agent security checklist?

Yes, and it's quicker for them than for large companies. A small business usually has a handful of agents and a short list of people who approve things, so the whole AI agent security checklist fits in an afternoon.

Who should own AI agent security in a small business?

The owner, or a person the owner names for each agent. An IT provider can set things up, but someone inside the business decides what each agent may do and answers for it.

What's the first AI agent control to put in place?

Human approval for anything that leaves the building: email, posts, payments and deletions. It's the control that limits the damage from almost every other mistake while you work through the rest.

Is an AI agent security checklist enough on its own?

It's a starting point. An AI agent security checklist tells you which controls should exist, and the system you run your agents on has to enforce them every day. Choose tools where approvals, separate identities and the log are built in, so a check you've passed stays passed.

Is there a standard AI agent security checklist I can follow?

There's no single official checklist yet. This one draws on the OWASP Top 10 for Agentic Applications, the joint agency guidance Careful adoption of agentic AI services, NIST CSF 2.0 and, for Massachusetts businesses, 201 CMR 17.00.

Should I run the AI agent security checklist on agents I already use?

Yes. Run it on every agent that already touches company email, files or customer data, and again whenever an agent's job or tools change. Start with the agents that can send, pay or delete, because those need a person's approval first.

Keep reading

  • A heavy threshold gate lets one cleared path through while dozens of pink trails stop at it.

    Start here

    Agentic AI security

    Agentic AI security explained for owners: identity, least privilege, approvals and an audit trail for AI agents, from the team that runs them in Massachusetts.

    Brian Gagne

  • A blurred hub drowns in pink cables while a clean hub in front holds one amber line.

    Identity and access

    AI agent permissions

    AI agent permissions decide what an agent can read, change and send. How to scope its tools, catch permission drift and run an access review.

    Brian Gagne

  • A pink stream of light is held at a round amber valve gate, waiting for a person's yes before anything leaves.

    Oversight

    Human approval for AI agents

    Human approval for AI agents that people actually read: which actions need a yes, how to avoid approval fatigue, and how standing approvals work.

    Amelia Gagne

  • A column of stacked plates with pink-lit seams sealed by an amber top.

    Oversight

    Audit trails for AI agents

    An AI agent audit log proves what an agent did, who asked and who approved it. What to record, how to keep it tamper evident, and how long to keep it.

    Amelia Gagne

  • Ten black pillars veined with pink fractures stand in a row, and three amber rings thread through every one of them.

    Threats

    OWASP Agentic Top 10

    The OWASP Agentic Top 10, ASI01 to ASI10, explained for owners: each risk in everyday terms, a small-business example, and the control that answers it.

    Brian Gagne

  • Reference

    Glossary

    An agentic AI glossary in plain words: AI agents, agentic IAM, non-human identities, prompt injection, shadow AI, MCP and more, each with a short definition.

Most MSPs are resellers. Kief Studio is the manufacturer.

A reseller sends your problem to the company that made the software. We are that company: we build LTFI and run it, so the people you talk to can change it. Book a walkthrough and see it on your own business.

Nothing plays until you press play.