AI engineering glossary · Evals guardrails AI security
What is spotlighting?
Spotlighting: A family of defences against indirect prompt injection that marks untrusted content, for example by delimiting it, encoding it or inserting special markers, so the model can tell data from instructions. It reduces but does not remove the risk.
Spotlighting: an example
Untrusted web text is wrapped in special markers, and the prompt tells the model never to follow instructions found between them.
Related terms
More Evals guardrails AI security terms
- STRIDE threat model
- Structured output validation
- SWE-bench
- Synthetic test data
- System prompt extraction
- Threat modelling
- Tool poisoning
- Tool-call accuracy
Where you learn it
Spotlighting is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.