Gli LLM stanno lentamente rivoluzionando il settore dei sistemi di analisi statica del codice per rilevare vulnerabilità. Finora erano prevalentemente basati su regole ma gli LLM specialmente di reasoning sono molto superiori perché sono in grado di fare collegamenti del codice e valutazioni dettagliate.
Qua ce ne sono alcuni con relativa recensione.
My general summary is as follows:
- Multiple AI-native SASTs are already on the market, ready to use today.
- They work extremely well.
- They find real vulnerabilities and logic bugs in minutes.
- They can “think”/”reason” about business logic issues.
- They can match developer intent with actual code.
- They aren’t based on static rule-sets and queries.
- They have low false positive rates.
- They’re cheap (for now).
- My results showed that (in order of success for finding vulnerabilities), ZeroPath, Corgea, and Almanax, are the top three products on the market right now. I did not test DryRun. However, all three products have different functions and can solve different problems, so I would recommend testing all of them if you can.










