I don't think I'm ready to trust very security sensitive functions to pure vibe-coded software, and that's what this seems to be? Certainly the README is authored by an LLM, and there's a gazillion empty commits and other weirdness that indicates no human is in the loop. It looks like a loop engineered this software. Models have gotten good, but c'mon. Good idea, maybe even a good implementation, but I don't have con…
How you type is a poor proxy for code quality. Code quality is a good proxy for code quality. Inspect the code, build a verification pipeline for it, use agents to explore the code and the architecture, see if you can unearth anything fowl.
And, it's not my monkey. You can inspect the code, build a verification pipeline for it, use agents to explore the architecture and see if you can unearth anything fowl.
My heuristic is to dismiss purely vibe-coded apps from people I don't know, particularly for security sensitive stuff. If the README is written by a human and is coherent and exhibits some kind of desire and competence to make good software on the part of the author, I'm more likely to trust they drove their agents with care.
Here's the thing: you can make good software with agents, if you exhibit good judgement and put yourself in the path as a gate on quality. Too many clues point at this being loop engineering. And, C for this task, given 100% agent authorship, gives me the ick. Seems like bad judgement or opting out of making judgement calls.