Reg. No. 40203410806 VAT LV40203410806

Theme

Book a consultation Book

06 / 11 AI red-teaming · LLM

Test an AI assistant for information disclosure

Assess whether a customer-facing chatbot can be induced to disclose its system prompt, embedded secrets or other restricted information.

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

Skills covered

  1. 01 Testing whether an LLM discloses its system prompt
  2. 02 Recognising sensitive information that must not be included in prompts
  3. 03 Reducing information-disclosure risk in AI assistants

More simulations

10
  1. 01 Identify a phishing email Red team · Phishing
  2. 02 Identify a fraudulent support call Social engineering · Voice
  3. 03 Detect indirect prompt injection AI red-teaming · LLM
  4. 04 Verify a suspected deepfake request Social engineering · Synthetic media
  5. 05 Identify invoice-redirection fraud Fraud · BEC
  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