Reg. No. 40203410806 VAT LV40203410806

Theme

Book a consultation Book

03 / 11 AI red-teaming · LLM

Detect indirect prompt injection

An AI assistant is about to process a document containing hidden instructions. Identify the injection before the system performs an unsafe action or discloses data.

AI red-teaming · LLM Desktop and sound recommended
03 Interactive 3D simulations · desktop and sound recommended

Skills covered

  1. 01 Detecting hidden instructions inside content
  2. 02 Treating untrusted content as data rather than instructions
  3. 03 Deciding when to block an AI action and escalate

More simulations

10
  1. 01 Identify a phishing email Red team · Phishing
  2. 02 Identify a fraudulent support call Social engineering · Voice
  3. 04 Verify a suspected deepfake request Social engineering · Synthetic media
  4. 05 Identify invoice-redirection fraud Fraud · BEC
  5. 06 Test an AI assistant for information disclosure AI red-teaming · LLM
  6. 07 Recognise social-engineering techniques Social engineering · Human factors
  7. 08 Assess an unapproved cloud application Attack surface · Shadow IT
  8. 09 Assess what a social-media post reveals OSINT · Oversharing
  9. 10 Identify credential-stuffing risk Credentials · Account security
  10. 11 Manage the first hour of an incident Incident response

All simulations