On Mon, 15 Jun 2026, at 08:12, Thomas Stromberg wrote: > TL;DR - We're building an automated local reverse-engineering and detection > platform, powered by tiny local deterministic AI models, retrained constantly > based on recent attacks and threat feeds.
Hi Thomas, Thanks for building this! I saw you mentioned something like -l0 for adjusting the detection sensitivity towards paranoid. Is this settable via a env var? It would great to have a default wired into a hook, then override it if it gets too sensitive. All, Has anyone the paru-fu to hook this to auto run and halt upon detection? I saw aurscan only mentioned hooking yay. It would be great to have a paru option also Cheers, Tom
