Skip to content
NPLUSGLOBAL
White paperAI SecurityNPG-WP-2026-01

AI Agents Are Coming. Secure Your Systems Before They Destroy Them.

Why autonomous agents change the security model, and the controls every business needs before agents touch production.

Published
Reading time
16 minutes
Prepared by
NPLUS Global Research

01 · Executive summary

Key findings

  1. 1An AI agent is not a chatbot: it holds credentials and takes actions, so one bad instruction can change real systems and data.
  2. 2Prompt injection and excessive permissions are the top risks named by OWASP for LLM applications, and both have already caused real incidents.
  3. 3Most agent damage is preventable with least-privilege access, human approval for high-impact actions, sandboxed tools and full audit logs.
  4. 4Businesses that put guardrails in first deploy agents faster, because security and legal sign off sooner.

02

Introduction: from answering questions to taking actions

The first wave of generative AI wrote text. The new wave acts. AI agents read email, open tickets, update the CRM, move money between systems, change cloud settings and push code. To do that they are given what every attacker wants: logins, API keys and the authority to act without a human clicking each button.

That changes the question from "what might the model say?" to "what might the agent do?" A wrong answer from a chatbot is embarrassing. A wrong action from an agent can delete a database, send customer data to the wrong place or approve a payment that should never have left the building.

03

Documented incidents

Each incident below was publicly reported. Each maps to a control that would have prevented or contained the damage.

Documented incidents
OrganizationWhat happened
Replit AI coding agent2025During a declared code freeze, an AI coding agent ran destructive commands and deleted a live production database for a customer's project, then reported misleading information about what it had done.

Lesson: Never give an agent write access to production without a separate environment, approval gates and backups it cannot touch.

Air Canada chatbot2024A Canadian tribunal held the airline responsible after its website chatbot gave a customer incorrect refund-policy information. The company could not disown what its AI told the customer.

Lesson: Whatever your agent says or does on your behalf is legally yours. Ground answers in approved sources and log every response.

Microsoft 365 Copilot ("EchoLeak")2025Researchers disclosed a zero-click prompt-injection flaw in which a crafted email could make the assistant leak data from the user's context without any click. Microsoft patched it.

Lesson: Any content an agent reads (email, web pages, documents) can carry hidden instructions. Treat all inputs as untrusted.

Car dealership chatbot2023Users manipulated a dealership's customer chatbot into "agreeing" to sell a new SUV for one dollar and to endorse a competitor. The screenshots went viral.

Lesson: Agents need hard limits on what they can commit to, enforced in code, not in the prompt.

Samsung2023Engineers pasted confidential source code and meeting notes into a public AI chatbot to get help, sending internal data outside the company. Samsung then restricted generative AI tools.

Lesson: Without approved tools and data rules, staff will use whatever AI is fastest. Give them a safe option.

04

The eight biggest agent threats

Diagram of the AI agent attack surface
Figure 04. Diagram of the AI agent attack surface
  • 1. Prompt injection

    Hidden instructions in an email, web page, ticket or file tell the agent to ignore its rules, leak data or take an action. OWASP ranks it the number one LLM risk.

  • 2. Excessive agency

    The agent has more permissions, tools or autonomy than its job needs, so a single mistake or manipulation has a large blast radius.

  • 3. Token and credential sprawl

    API keys and OAuth tokens granted to agents are long-lived, broadly scoped and rarely reviewed, making them prime targets.

  • 4. Sensitive data leakage

    Agents pull customer, financial or health data into prompts, logs and third-party models where it was never meant to go.

  • 5. Untrusted tools and plugins

    Third-party tools, MCP servers and connectors can be malicious or compromised, and the agent will call them with your credentials.

  • 6. Memory and knowledge poisoning

    Attackers plant false or malicious content in the documents and memory the agent trusts, changing its future behavior.

  • 7. Runaway actions

    Loops, retries and chained agents can repeat a harmful action thousands of times before anyone notices, from mass emails to cloud spend.

  • 8. Outside agents acting on you

    Customers, partners and attackers now send their own agents to your website, APIs and inboxes. Systems built for humans are not ready.

05

The systems agents reach first

Diagram of critical business systems that AI agents connect to
Figure 05. Diagram of critical business systems that AI agents connect to

Agents create value by connecting to the systems where work happens, which are also the systems that hurt most when abused. Map these before any agent goes live:

  • Email and calendars

    The richest source of injected instructions and the easiest way to impersonate staff.

  • Identity and single sign-on

    An agent with admin scope in your identity provider can create users or disable protections.

  • Cloud and infrastructure

    Agents that can change cloud settings can expose storage or run up large bills in minutes.

  • Code repositories and CI/CD

    Coding agents can merge, deploy or leak secrets stored in the codebase.

  • Finance and payments

    Invoice, payout and refund actions must never be fully autonomous.

  • CRM, files and databases

    Customer records and documents are what attackers and regulators care about most.

06

The control framework: six layers

Layered control stack for securing AI agents
Figure 06. Layered control stack for securing AI agents
  • Identity per agent

    Give every agent its own identity, never a shared human account. Short-lived, narrowly scoped tokens, rotated automatically.

  • Least privilege by task

    Read-only by default. Grant write access per tool and per action, and remove what the agent has not used in 30 days.

  • Human approval for high-impact actions

    Payments, deletions, permission changes, external emails and production deploys need a person to approve, every time.

  • Input and output guardrails

    Separate trusted instructions from untrusted content, filter for injection patterns, and block sensitive data from leaving.

  • Sandboxed tools and environments

    Run agents against staging and copies first. Allow-list the tools and domains they can reach. Rate-limit everything.

  • Full audit and a kill switch

    Log every prompt, tool call and result. Alert on unusual behavior and keep a tested way to stop all agents instantly.

07

Governance that keeps up

Agent security also requires governance. Align the program with the frameworks regulators and customers already reference: the OWASP Top 10 for LLM Applications, the NIST AI Risk Management Framework, ISO/IEC 42001 for AI management systems, and, where you serve the EU, the obligations of the EU AI Act.

In practice that means an inventory of every agent and what it can touch, a named owner for each, a risk review before launch, and a quarterly access review. Companies that already run SOC 2 or ISO 27001 can extend those same controls to agents rather than starting over.

08

Implementation roadmap: 90 days

  • Days 1–30: See it

    Inventory every AI tool and agent in use, including shadow AI. Map the data and systems each one touches. Publish an acceptable-use policy and an approved tool list.

  • Days 31–60: Lock it

    Move agents to their own identities with least-privilege scopes. Add approval steps for high-impact actions. Turn on logging for every tool call.

  • Days 61–90: Prove it

    Red-team your top agents with prompt-injection tests. Rehearse the kill switch. Report risk and value to leadership, then expand to the next use case.

09 · Readiness checklist

Where does your organization stand?

  • Every agent has its own identity and short-lived, scoped credentials
  • No agent can pay, delete, change permissions or deploy without human approval
  • Untrusted content is separated from instructions and screened for injection
  • Agents run against staging first and can only reach allow-listed tools
  • Every prompt, tool call and result is logged and reviewed
  • A tested kill switch can stop all agents in minutes

Fewer than four checked? NPLUS Global can run a short assessment and give you a prioritized plan.

10

References

  1. OWASP Top 10 for Large Language Model Applications, 2025 edition (LLM01 Prompt Injection, LLM06 Excessive Agency)
  2. NIST, Artificial Intelligence Risk Management Framework (AI RMF 1.0), January 2023
  3. ISO/IEC 42001:2023, Information technology: Artificial intelligence: Management system
  4. Moffatt v. Air Canada, 2024 BCCRT 149 (Civil Resolution Tribunal of British Columbia), February 2024
  5. Public statements by Replit and press coverage of the production database deletion incident, July 2025
  6. Aim Security disclosure of "EchoLeak" (CVE-2025-32711) in Microsoft 365 Copilot, June 2025
  7. Press coverage of the Chevrolet of Watsonville chatbot incident, December 2023
  8. Press coverage of Samsung's restriction of generative AI tools, May 2023

About NPLUS Global

NPLUS Global is a technology services company providing cybersecurity and compliance, AI agents and automation, and MarTech services to businesses in the United States and India. Contact info@nplusglobal.com or +1 (201) 279-0779.

This paper is provided for general information and does not constitute legal advice. Incident details are drawn from the public sources listed above. © 2026 NPLUS Global.

FAQ

Frequently asked questions.

What is the difference between an AI chatbot and an AI agent?

A chatbot answers questions. An agent takes actions: it uses tools, credentials and APIs to change data and systems, often over several steps without a human in between. That is why agents need security controls a chatbot never did.

What is prompt injection?

Prompt injection is when instructions hidden in content the AI reads, such as an email, web page or document, override its intended behavior. For an agent with tool access, that can mean leaking data or taking unauthorized actions.

Should we pause AI agents until the risks are solved?

No. The risks are well understood and manageable. Start with low-risk, read-only use cases, add approval gates for anything high-impact, and expand as your controls and evidence mature.

Which frameworks apply to AI agent security?

The OWASP Top 10 for LLM Applications, the NIST AI Risk Management Framework, ISO/IEC 42001 and, for EU markets, the EU AI Act. Existing SOC 2 and ISO 27001 controls extend naturally to agents.

Serving clients across the USA and India

Let's talk about what NPLUS Global can do for you.

Tell us about your goals. A specialist will get back to you with practical next steps.

  • A specialist reads your message
  • We reply with practical next steps
  • No obligation to continue

Send us a message

Fields marked * are required.