Skip to content
Mardi Gras Developers
Menu+

Security

AI security check

Ten questions about how you use AI. You immediately see a score per area and the three measures that pay off most. It takes about three minutes.

Your answers stay in your browser and are not stored or sent anywhere. This is a first estimate, not an audit.

The ten questions follow the two current OWASP lists for AI security. Each measure states which risk it addresses. OWASP Top 10 for LLM Applications (2025), OWASP Top 10 for Agentic Applications for 2026.

Updated

0 of 10 answered

  1. 01 · Data and privacyDo you know in which region your prompts and completions are processed?
  2. 02 · Data and privacyIs personal data masked before it goes to a model?
  3. 03 · AccessDo staff use public AI tools with company or customer data?
  4. 04 · AccessHow is your AI environment or AI application reached?
  5. 05 · Untrusted inputHow does your AI handle outside content such as emails, documents and web pages?
  6. 06 · Untrusted inputDo you test your AI application for prompt injection?
  7. 07 · Agents and permissionsWhat permissions does an AI agent or AI integration have in your systems?
  8. 08 · Agents and permissionsIs human approval required for risky actions such as deleting, paying or deploying?
  9. 09 · Oversight and qualityCan you reconstruct afterwards what an AI application or agent did?
  10. 10 · Oversight and qualityDo you measure the quality of AI answers on every change?

Pick an attack and see where it stops

Five attacks that happen every day, and the layer that stops each one.

Scanner hunts a known vulnerability
Stopped: Zero Trust. As soon as a flaw in widely used software becomes public, bots scan the whole internet within hours for servers that still have it. With Cloudflare Zero Trust the server opens an outbound tunnel itself and no port is open; a request without a valid identity never reaches the application, even when it has not been patched yet. Patching is still needed, but it buys you time.
Stolen password
Stopped: Zero Trust. Passwords leak through phishing and reuse. Behind Zero Trust a password alone is not enough: sign-in goes through your identity provider with a second factor, per application, and access can be revoked at once when someone leaves.
Hidden instruction in a document
Stopped: Input. An attacker hides a command in a PDF or email that an employee asks the AI to summarise. Because external content stays separated from the instruction, the text is summarised and not carried out. This layer is not watertight, which is why two more follow.
Manipulated agent looks for secrets
Stopped: Permissions. Suppose an injection does succeed and the agent is told to look up passwords or keys. The agent only has permissions for its task and cannot reach them.
Agent wants to deploy or delete something
Stopped: Approval. An agent, manipulated or simply wrong, prepares an irreversible action. It is only carried out after a human has looked at it and approved it.

Every step is in the audit log, including the blocked ones.

All ten measures

The full list the check is based on, also usable as a checklist.

  1. Data and privacy

    Enforce the processing region technically

    Route all model requests through a gateway that only allows European endpoints and refuses requests for which that is not possible.

    OWASP: LLM02 Sensitive Information Disclosure

    Private AI platform
  2. Data and privacy

    Mask personal data automatically

    Replace structured data deterministically and run free text through PII detection, so it does not depend on staff paying attention.

    OWASP: LLM02 Sensitive Information Disclosure

    Data engineering
  3. Access

    Give staff an AI environment of their own

    A ban only works with a good alternative. Offer your own chat environment that is just as easy and where you decide where data goes.

    OWASP: LLM02 Sensitive Information Disclosure

    Private AI platform
  4. Access

    Put identity checks in front of the application

    Let nobody reach the application without first signing in through your identity provider, and also check that admin screens are not directly on the internet.

    OWASP: ASI03 Identity & Privilege Abuse

    AI infrastructure and security
  5. Untrusted input

    Treat external content as data

    Mark everything that comes from outside as untrusted and keep it separate from the instruction, so hidden instructions in a document are not read as a command.

    OWASP: LLM01 Prompt Injection · ASI01 Agent Goal Hijack

    AI infrastructure and security
  6. Untrusted input

    Make attack tests part of every release

    Record a set of known attacks and run it automatically on every change, just like ordinary tests.

    OWASP: LLM01 Prompt Injection

    AI infrastructure and security
  7. Agents and permissions

    Give agents least privilege

    Give every agent its own account with only the permissions for its task. What an agent may not do, an attacker cannot make it do either.

    OWASP: LLM06 Excessive Agency · ASI03 Identity & Privilege Abuse

    AI infrastructure and security
  8. Agents and permissions

    Have a human approve risky actions

    Decide which actions are irreversible or costly and let the AI only prepare them. A human carries them out or approves them.

    OWASP: LLM06 Excessive Agency · ASI02 Tool Misuse

    AI solutions and agents
  9. Oversight and quality

    Record every action in an audit log

    Record per action who or what performed it, with which input and with what result, in a place the agent itself cannot change.

    OWASP: ASI10 Rogue Agents · ASI08 Cascading Failures

    AI infrastructure and security
  10. Oversight and quality

    Measure quality with a fixed test set

    Compile a set of real questions with expected answers and measure every version against it, so you see whether a change improves or degrades.

    OWASP: LLM09 Misinformation

    AI solutions and agents