Security Review for AI Automation: A Practical Checklist

Start here

Overview

Security reviews should be proportional: risk-tiered controls for internal ops automation vs customer-facing agents.

Core concept

Definition

A practical AI security review examines data classification, model providers, prompt injection surfaces, tool permissions, secret storage, and incident response for automation failures.

Business impact

Why it matters

AI expands attack surface: tools can exfiltrate data if mis-scoped; prompts can be manipulated if user content is unconstrained.

Practical model

Framework

Data flow diagram

Where prompts and retrieved docs travel; where outputs land.

Least privilege

Separate service accounts per integration; rotate keys.

Implementation detail

Detailed breakdown

Red teaming prompts

Test jailbreaks specific to your templates and tools.

In practice

Real-world example

A healthcare vendor blocked external URLs in support chat inputs after tests showed credential phishing attempts via prompts.

Avoid these

Common mistakes

Shared API keys across tenants.
No rollback plan when a model provider has an incident.

Engineering layer

Technical patterns

Threat modeling for agents

STRIDE on tool-calling paths: spoofed webhooks, tampered documents, over-privileged API keys.
Separate network egress for model calls vs internal DB.

Build patterns

Code examples

Egress allowlist check

Outbound fetch restricted to approved domains.

TypeScript

const ALLOW = new Set(['api.openai.com', 'api.anthropic.com']);
export function assertAllowedUrl(url) {
  const host = new URL(url).host;
  if (!ALLOW.has(host)) throw new Error('egress_denied');
}

System view

System architecture

YAML

[Architecture diagram + data flow]
        → [Classification]
        → [Control matrix: authZ, secrets, network]
        → [Residual risk + compensating controls]
        → [Sign-off artifacts]

Keep learning