Security · 1 August 2026 · 11 min read

A security review checklist for enterprise AI systems

What to ask before an AI system reaches production. Written to be handed to a security team that has not reviewed one before.

Most security teams reviewing their first AI system reach for the application security checklist they already have. It covers perhaps half of what matters, and the half it misses is where the interesting failures live.

This checklist covers the AI-specific surface. It assumes your existing controls — network, identity, patching, secrets, logging — are already applied. Use it alongside them, not instead.

Take it and use it. No attribution required. If it saves a review cycle it has done its job.

1. Data boundary

The first question, and the one that eliminates the most architectures.

That last one catches people. Several popular LLM observability platforms are hosted, and teams wire them up without registering that full prompt content is now leaving the perimeter.

2. Retrieval and entitlements

The most common serious finding we see, and rarely caught by generic review.

The aggregation question is the subtle one. A user may legitimately have access to a hundred documents individually while the synthesis of all hundred constitutes information they were never meant to hold. Traditional access control has no concept of this. Decide deliberately whether it matters in your context.

3. Prompt injection

Direct injection — a user typing adversarial instructions — is the easy case. Indirect injection, where instructions arrive inside content the system retrieves, is the hard one.

A useful framing for reviewers: assume injection succeeds. Now ask what the attacker can do. If the answer is "read one document the user could already read", the risk is manageable. If it is "send email as the user", it is not.

4. Agent authority

Where an AI system can take actions, the security question shifts from data to authority.

5. Output handling

Model output is untrusted input to whatever consumes it next. This is a classic vulnerability class wearing new clothes.

The markdown image exfiltration path is worth checking specifically: a model induced to emit an image tag pointing at an external host, with sensitive content encoded in the URL, will cause the user's browser to make that request when the response renders.

6. Supply chain

7. Evaluation and monitoring

Security review of an AI system should ask about quality, because a confidently wrong answer in a clinical or financial context is a safety issue rather than a product defect.

8. Audit evidence

Someone will eventually ask what the system did and on what basis. Design for that question rather than reconstructing an answer under pressure.

How to use this

Run it as a design review during architecture, not as a gate before launch. Every item above is cheap to address while the design is fluid and expensive once the system is built.

If you are reviewing a system that already exists, work top-down. Data boundary and retrieval entitlements are where the findings that stop deployment usually are — and they are also the two that are hardest to retrofit.

The mapping to formal frameworks — NIST AI RMF, ISO/IEC 42001, and the OWASP Top 10 for LLM Applications — is worth doing once, so findings land in a process your organization already runs rather than in a document nobody owns.

Related

Stuck at one of these?

The assessment diagnoses which constraint is actually blocking you, and produces a roadmap you own — executable by us, by another firm, or by your own team.

Direct response from an engineer. Typically within one business day.