[Misdetection/Security] PHP file misdetected as txt due to low-confidence fallback

I initially reported this to the Google OSS VRP (https://g.co/vulnz).
They acknowledged it as a valid product vulnerability. However, because Magika is classified as an OT2 project, they require a patch to be committed and merged before they can process the report.
They encouraged me to open a public issue to collaborate with the maintainers on a fix, so I am doing that here.

Magika extracts features only from the beginning and end of a file (`beg_size=1024`, `end_size=1024`). For files smaller than 1024 bytes, both feature windows contain the exact same content.

Knowing that the goal was simply to keep the score below 0.5, I used Claude to help craft a PoC.

In the PoC below, the file is 958 bytes long: roughly 928 bytes of HTML/JS followed by a 30-byte `` block. Because the HTML/JS content dominates both feature vectors, the PHP signal is relatively weak.

As a result, the model predicts `dl=php`, but with a score of about 0.489. Due to the low-confidence fallback in `python/src/magika/magika.py`, the final result becomes `output=txt`. In other words, Magika returns `txt` for a file that it internally considers likely to be PHP.

This is also highly position-sensitive. If the PHP block is moved slightly, the score fluctuates across the threshold (for example, 0.506, 0.489, and 0.646). This appears consistent with the current feature extraction design and with where the PHP bytes land inside the two feature windows.

The attached PoC reproduces this behavior and shows that the PHP interpreter still successfully executes the sample.

Because this is my first time handling a security issue through a public issue tracker, I was not sure whether including the full PoC here would be appropriate, so I have not attached it for now.

Start in python/src/magika/magika.py, focusing on the low-confidence fallback and the feature handling described for files under 1024 bytes. Reproduce the reported case with a mostly HTML/JS file ending in a short PHP block, if the PoC can be obtained. Done means the vulnerable sample is no longer returned as txt while preserving the intended fallback behavior.

Written by the indexing model from the issue text.