Prompt injection
An attack where instructions ride in on data the model treats as trustworthy, such as a retrieved document or a web page, and override the developer prompt.
Why exams ask this
Responsible-AI sections test the mitigation, not the definition. The honest answer is that no prompt wording fully solves it, so the control is at the tool and permission boundary.
Relevant to
AI Fluency: Framework and FoundationsGenerative AI FundamentalsGenerative AI LeaderOCI Generative AI ProfessionalAI Agents CourseGenerative AI and LLMs, NCA-GENLAI Engineering Professional CertificateCertified Machine Learning Engineer, AssociateClaude Code in ActionClaude Certified Architect, Foundations
Related concepts
Resources
No resources linked to this concept yet.