Library › Cybersecurity AI › HR and recruiting

Spot a malicious job application before opening it

  • For HR and recruiting
  • You practice Giving the right context
  • Time about 5 minutes

About this exercise

A recruiter on your team asks if she can open this application. Reply with a first line 'Don't open it yet', then exactly 3 numbered red flags quoting the email, then one line starting 'Instead:' that follows your recruiting security rule. Plain text, under 90 words.

Common mistakes when you ask AI for this

  • Flagging normal things. The AI calls the personal email address suspicious, which is normal for job seekers. Try: Say: "Personal emails and the job reference are normal. Flag only real warning signs."
  • Generic safety advice. The AI says 'scan it with antivirus' instead of your team's rule. Try: Add: "Use handbook 6.4: ATS only, re-apply through the careers page."
  • No clear answer first. The AI explains before saying whether to open it. Try: Ask: "First line: Don't open it yet."
  • Too many red flags. The AI lists every possible warning sign in a long list. Try: Be exact: "Exactly 3 numbered red flags."
  • Trusting the AI to count words. AI is bad at counting. Ask for "under 90 words" and it often lands well over. Try: Ask for less than the limit and cap each line: "each line under 15 words, under 70 words total."
  • Letting markdown in. AI adds bold and headings by default, and in a chat reply they show up as stray symbols. Try: Add: "Plain text only, no bold, no headings."

What a strong prompt includes

  • Puts the answer first
  • Asks for quotes
  • Uses your rule
  • Says exactly how many
  • Asks for plain text

Practice this now ↑

Related exercises