Stage 1 · Lesson 5 of 7
The web weaknesses AI apps inherit
Most LLM apps are web apps, so the classic weaknesses still apply, and several come back through the model. happens when untrusted text is pasted into a query or command. Cross-site scripting (XSS) happens when untrusted text is shown in a page as code.
Broken lets one user reach another's data. (SSRF) tricks a server into fetching an internal address. Now replace "untrusted text" with "model output" and you have several LLM risks: a model answer rendered as HTML, a generated SQL query run as is, a URL the agent fetches.
If you know the classic fixes, such as output encoding, parameterised queries, access checks on every request and for outbound requests, you already know half of AI app defence.
Common traplearning AI security without ever learning the web basics.
A question to check yourself, an AI practice session and 2 cheat sheet entries come with the full roadmap. Unlock
Resources for this stage
Start with· follow one of these
- RoadmapFreeSefism Cybersecurity Roadmap
Sefism · Beginner
Sefism's general security roadmap, for any foundation in this stage you want to study in more depth
- CourseFreeProfessor Messer's Security+ (SY0-701) Course
Professor Messer · Beginner
Free videos covering the core security concepts, from access control to cryptography
Practise
Keep handy
Also worth your time
The four questions, diagrams and STRIDE in one practical page
- roadmap.sh: Cyber SecurityGo deeper
A map of the wider security field, so you know where AI testing sits