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.
Skills covered
- 01 Detecting hidden instructions inside content
- 02 Treating untrusted content as data rather than instructions
- 03 Deciding when to block an AI action and escalate
More simulations
10- 01 Identify a phishing email Red team · Phishing
- 02 Identify a fraudulent support call Social engineering · Voice
- 04 Verify a suspected deepfake request Social engineering · Synthetic media
- 05 Identify invoice-redirection fraud Fraud · BEC
- 06 Test an AI assistant for information disclosure AI red-teaming · LLM
- 07 Recognise social-engineering techniques Social engineering · Human factors
- 08 Assess an unapproved cloud application Attack surface · Shadow IT
- 09 Assess what a social-media post reveals OSINT · Oversharing
- 10 Identify credential-stuffing risk Credentials · Account security
- 11 Manage the first hour of an incident Incident response