Security Advisor · Runs on ChatGPT GPT-5.5 · 5 cr./message

AI assistant: how not to give away too much

Account and data protection, review of suspicious emails and links, sensible settings without paranoia.

What Security Advisor returns

The shape of the answer is fixed in advance: recognize phishing, limit access, configure backups, recover after a breach, store documents and correspondence safely. Two conversations about the same task therefore end in the same form: the answer can be compared with the previous one and passed on without asking for a rewrite.

“You help DEFEND: set up two-factor authentication and a password manager, recognize phishing, limit access, configure backups, recover after a breach, store documents and correspondence safely.”

What Security Advisor will not do

The role has 6 rules, 3 prohibitions among them outright. We quote them as written rather than paraphrase: promising “it can do anything” is cheaper, but then people meet the limit only after paying for a message. Here it is visible beforehand, and a neighbouring role can be picked straight away.

“You do not help attack: never write malicious code or explain breaking into accounts, devices or networks, or bypassing protection, even framed as a test — refuse and offer a lawful alternative such as an official vulnerability program on the user's OWN system.”

“Never request or accept passwords, one-time codes, secret keys or document scans; if the user sends them, tell them to rotate and do not repeat them.”

“Do not invent vulnerabilities in specific services or versions and do not give legal conclusions; for crimes, recommend contacting law enforcement and the service's support.”

How Security Advisor runs the review

Below is how the role holds the review: the rules are given before your first message and do not shift with mood. Manner can only be shown honestly by quoting, so these are the exact words.

“You advise on practical security for ordinary people and small teams.”

“Order risks by likelihood and consequence rather than by how scary they sound, and start with what closes the most for the least effort.”

What a message to the “How not to give away too much” role costs

You are charged per message sent, not per month of access: a role needed once a quarter costs nothing in between, and it needs no line of its own in the budget.

5 credits per message

The price is the same for a short and a long message: what counts is the send, not the length.

No subscription fee

Ten messages a month cost the price of ten messages: you pay for what happened, not for a plan.

Three questions Security Advisor offers first

A click opens the chat with the message already typed. These are not our examples but the role’s own suggestion: the same three lines stand in the empty conversation window.

Check whether this email is safe

How to protect my accounts

What to do after a breach

Questions about this assistant

Quick answers

Yes: the send is charged, not the quality of the answer — 5 credits per message. That is exactly why the role starts with clarifying questions: one precise question costs less than three vague ones.

ChatGPT GPT-5.5. A role is character and rules, but a model executes them, so the model is fixed for this assistant: a weaker one would turn analysis into paraphrase, an unnecessarily strong one into overpaying. You can switch models inside the chat.

Both roles sit on the “Code and technology” shelf but answer by different rules: the rules of Security Advisor are quoted in full on this page, and those of “Prompt Engineer” on its own. The full shelf is listed at the end of this page.

Yes, the conversation stays in your account history: you can return to it, continue from the same point or start over.

An assistant is AI, not a person: it helps with a task but does not replace a doctor, therapist, lawyer or other qualified professional. Verify important decisions and facts against a primary source.

How Security Advisor differs from a plain chat

In a plain chat the framing is on you: the order of questions, the limits, the requirements for the answer — from scratch in every new window. Here it is already written: 6 rules, 3 prohibitions of them, all quoted on this page. You never have to restate them.

✓ Rules: 6, prohibitions: 3
✓ Catalogue shelf: Code and technology
✓ A program answers, not a person: it replaces no doctor, lawyer or therapist