attacks in user- input • With API in python, lua and php • Introduced at Black Hat USA 2012 • Open source with BSD license • https://github.com/client9/libinjection
expressions • No unit tests • No performance (speed) tests • No coverage tests • No accuracy or precision tests • No false positive tests • “what are they actually doing?”
tokenization algorithm (text “<b>foo</b>” to tags <b>, foo, </b>) • The goal is to change the context to ‘javascript’ and execute arbitrary code. • This seems detectable.
HTML differently. • This lead to a number of different attacks using broken html tags, special characters or encodings. • Now, most browsers now use the same algorithm from the HTML5 specification. • The HTML5 algorithm is very specific
have some spectacular failures (bypasses) • False-positive QA not completed. • Currently does not handle some IE injections • Does not have a test-bed for experimenting (maybe later this week). • More QA, code-coverage needed • No bindings for scripting languages (soon).