Viewing profile — jfaganel99

[flagged]

For the sceptics... The benchmark is research based with a published ArXiv paper on the methodology https://arxiv.org/abs/2604.13764

Question, because I can't answer it myself... Created an open-source benchmark for code security scanners and ran a bunch of them along with LLMs on real vulnerable code. Fable 5 i…

As promised here is the open-source GitRepo so you can give it a go with your tooling: https://github.com/kolega-ai/Real-Vuln-Benchmark Updated benchmark results published here als…

[dead]

Working on a model benchmark focused on which model is good for these tasks. Keep you posted

This is one of the most practical breakdowns I’ve seen for a while. The spec.md as a living architecture map is smart, and documenting auth guard pattern sites as new modules get a…

Author here. The finding that surprised me most while writing this wasn’t the breach numbers. It was the Stanford result: developers with AI assistance introduced more flaws than t…

That's a great question. This is how I would think about it: The number of vulnerabilities by itself doesn't mean much. It has more to do with the size of the codebase and the atta…

Hi HN - side project. After reading about the ClawHavoc campaign and seeing how fast malicious skills were spreading on ClawHub (1,100+ at last count), I figured it would be useful…

[flagged]

[flagged]

[flagged]

Author here. We built a security scanner called Kolega that does semantic analysis instead of pattern matching. To see if it actually worked, we ran it against 45 open source proje…