A large language model's (LLM's) fluent, confident output carries no inherent safety guarantee for whatever system processes it next. You will learn why the destination, not the origin, of generated text determines the scrutiny it needs, apply the injection defences this catalogue already teaches for databases, rendered web pages, and shells and file paths to model generated content specifically, and cover validation, context specific encoding, and the sharper risk of an agentic system where output becomes an action rather than only displayed text. The course closes with a practical review checklist and testing practice for every point output crosses a trust boundary. Every example uses a clearly labelled hypothetical application; no real exploited system is presented as fact.
Nothing. Every course, exam, and certificate on the catalog is free — including retakes. All you need is a free Safeguard account.
None. The flagship course, Safeguard Certified Practitioner, is a beginner-level course — basic familiarity with how software is built helps, but every exam question is answerable from the lessons themselves.
You can retake it after a 24-hour cooldown, as many times as you need. Retakes are free, and each attempt draws a fresh random set of questions.
The Safeguard Certified Practitioner credential is valid for 24 months from issue. The expiry date is printed on the certificate and shown live on its public verification page. Renewing means passing the current exam again.
