Reg. No. 40203410806VAT LV40203410806

+371 2256 5353 [email protected]

Theme

Book a consultationBook

03 / 11AI 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 · LLMDesktop and sound recommended
03Interactive 3D simulations · desktop and sound recommended

Skills covered

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

More simulations

10
  1. 01Identify a phishing emailRed team · Phishing
  2. 02Identify a fraudulent support callSocial engineering · Voice
  3. 04Verify a suspected deepfake requestSocial engineering · Synthetic media
  4. 05Identify invoice-redirection fraudFraud · BEC
  5. 06Test an AI assistant for information disclosureAI red-teaming · LLM
  6. 07Recognise social-engineering techniquesSocial engineering · Human factors
  7. 08Assess an unapproved cloud applicationAttack surface · Shadow IT
  8. 09Assess what a social-media post revealsOSINT · Oversharing
  9. 10Identify credential-stuffing riskCredentials · Account security
  10. 11Manage the first hour of an incidentIncident response

All simulations