Library › Cybersecurity AI › IT and security teams

Check an identity config against your security baseline

  • For IT and security teams
  • You practice Giving the right context
  • Time about 5 minutes

About this exercise

Review this exported identity and storage config against your company baseline: passwords at least 14 characters, MFA required for every user, legacy sign-in protocols blocked, storage buckets private, and sessions of 12 hours or less. List only the settings that break the baseline, as numbered lines like '1. setting: current value -> baseline value'. Plain text, under 70 words.

Common mistakes when you ask AI for this

  • Not giving the baseline. Without your rules, the AI judges against its own idea of best practice and flags extra things. Try: Paste the rules: "Baseline: passwords 14+, MFA for all, legacy auth blocked, buckets private, sessions 12 hours or less."
  • A security essay. The AI writes sections of general hardening advice, not a list of what breaks your baseline. Try: Add: "List only settings that break the baseline, one numbered line each."
  • Vague fixes. The AI says 'strengthen the password policy' instead of the value to set. Try: Show the shape: "setting: current value -> baseline value."
  • Trusting the AI to count words. AI is bad at counting. Ask for "under 70 words" and it often lands well over. Try: Ask for less than the limit and cap each line: "each line under 15 words, under 50 words total."
  • Letting markdown in. AI adds bold and headings by default, and in the change ticket they show up as stray symbols. Try: Add: "Plain text only, no bold, no headings."

What a strong prompt includes

  • Gives the baseline
  • Lists only failures
  • Shows the line shape
  • Sets a word limit
  • Asks for plain text

Practice this now ↑

Related exercises