Safety concerns on using eval() on a completion

[green tartan]

Any precautions I should take when using eval() on a completion's return?

I ask the AI to generate a Python list of possible options and use eval() to convert it to an actual list. I am using functions to ensure that it works as I intend. The prompt is sent by my script (not the user) but I want to know if there is anything I should be careful of.

Safety concerns on using eval() on a completion

[tepid bridge]

You should NEVER do it. At all, no exceptions. Do you mind sharing a code snippet of your usage, so that I could maybe see if there is another solution?