Ask HN: Which CVEs should I add to my Python security benchmark for AI agents?

A discussion on Hacker News is seeking input on which CVEs to include in a Python security benchmark for AI agents. The conversation is related to a GitHub project and a comments thread on the topic. The project and discussion can be found on GitHub and Hacker News, respectively. The discussion has garnered some attention, with a single comment submitted so far. The goal of the benchmark is to enhance security for AI agents in Python.