csnate
The project is currently 100% vibe coded with codex\gpt-5.5, but after running some experiments, I'm working on replacing some of the vibe coded SQL engine with Apache Calcite.
Feel free to reach out: [email protected]
So I dont want to give too much away about how it works because I think I might try to offer a paid version where the results are private.
But at a high level it combines an LLM, program analysis, and heuristics.
A binary static analysis tool that identifies vulnerabilities.
Right now, still just focused on buffer overflows. It can find some known CVEs and I’ve made several reliability improvements over the past month or so.
I think I’m going to expand to additional vulnerability types soon.
That said, I have found LLMs can find bugs in binaries. It’s not all false positives, as far as I can tell. I have a side project I’ve been working on that does just this (shameless plug): PwnScan.com. It’s currently free and focused on binaries.
The bad news is that you quickly get into a situation where you have too many false positives where it’s sometimes not feasible to sort through them all.
My current side project is a vulnerability scanner for binaries. I do VR in my day job, so im trying to figure out how useful (or not) AI is for this domain.
Jury is still out. Getting false positives and negatives, but I can find some known CVEs!
Show HN: I Made an AI-Powered Static Analyzer for Binaries
For at least a few years (since before COVID), in my circle everbody wants an AI tool that finds vulnerabilities in binaries. I have my reservations about such a tool because of my perception that AI is overhyped, so I decided to build one myself to see how useful it could be (or not).I was actually kinda surprised how well it worked for my collection of binaries with known CVEs. It definitely...
Downside though is that sometimes I end up “wanting to want.” Like, having a date night with the wife, social gatherings with food, or just the occasional indulgence.