Home / Insights / How to Secure AI Agents: A Practical Deployment Checklist

AI security field guide

How to Secure AI Agents: A Practical Deployment Checklist

Published 18 November 2026 · Dominion Fortress

An AI agent is not just a chatbot when it can call tools, read files, send messages, modify records or trigger workflows. Its security boundary includes the model, instructions, connected tools, identity, data sources and the actions it is allowed to take.

Start with the agent's authority—not its prompt

Prompt wording is not an access-control system. If an agent can delete records, transfer money, expose private files or execute commands, those capabilities must be constrained outside the model. Treat the agent as an application identity with explicit permissions and a defined blast radius.

Core rule: the model may recommend an action, but the application and its policy layer must decide whether that action is authorized.

1. Inventory every tool and action

2. Apply least privilege at the tool boundary

Give each tool a narrow permission set and enforce it server-side. A tool that can read one customer's records should not accept an arbitrary customer identifier without checking the caller's authorization. Validate object ownership, tenant boundaries, allowed fields and action parameters on every request.

3. Treat retrieved content as untrusted input

Documents, web pages, emails, tickets and code repositories may contain instructions intended to manipulate the agent. This is commonly discussed as indirect prompt injection. Retrieved content should be treated as data, not as a higher-priority instruction. Separate system policy from retrieved text, label untrusted sources and never let a document silently expand the agent's permissions.

4. Protect secrets and sensitive data

5. Put human approval around consequential actions

Require explicit approval for high-impact or irreversible actions, such as sending external communications, changing production settings, deleting data, issuing refunds or modifying access. Show the reviewer the exact action, target, relevant data and expected consequence. Approval must be bound to the action actually executed—not to a vague earlier instruction.

6. Validate tool inputs and outputs

Use strict schemas, allowlists, length limits and server-side validation. Never execute model-generated SQL, shell commands, URLs or code without a purpose-built safety layer. Constrain outbound network access where feasible, and defend against SSRF, path traversal, injection and unsafe file handling in the tools themselves.

7. Build an evaluation set before launch

Test normal tasks and adversarial cases. Include malicious instructions in retrieved documents, requests to access another tenant's data, attempts to reveal secrets, tool-parameter manipulation, conflicting instructions, oversized inputs and repeated tool-call loops. Measure both task success and policy violations. Re-run the evaluation suite after changing models, prompts, tools or retrieval sources.

8. Log actions so an incident can be reconstructed

Record the agent and user identity, model and configuration version, tool name, validated arguments, authorization decision, approval record, result status and correlation ID. Avoid logging secrets or unnecessary personal data. Make logs tamper-resistant and define alerting for unusual action volume, denied access and repeated policy failures.

9. Prepare a kill switch and recovery path

Deployment readiness checklist

Useful security references

Use established material as a starting point, then map controls to your actual architecture: OWASP Top 10 for LLM Applications, NIST AI Risk Management Framework and MITRE ATLAS.

Need an architecture review?

Dominion Fortress works across AI automation, software engineering and security. A review can examine tool permissions, data boundaries, retrieval design, approval gates, logging and adversarial testing within an agreed scope.

Explore AI securityDiscuss an AI security review

Related: AI agent development · LLM and RAG systems · API security · Methodology

This guide is general educational information. Project decisions should be based on the specific systems, risks, permissions and requirements involved.