Show HN: Can an AI Agent Bypass Your Website Security?
0 comments
- Points8
- Comments1
0 comments
As part of our red-teaming efforts, we recently configured GPT-6 Astra to test how easily an AI agent can bypass existing bot detection and human verification systems. We built a tool that lets you run the same test on your own website: https://assess.poh.org Enter your website URL, and we'll launch an AI agent to test your workflows, record its actions, and show how we evaluate the session. Below are three recorded tests. In the recorded tests below, agents were able to complete CAPTCHAs,…
Story details from Hacker News ↗ · linked article on assess.poh.org.
Show HN: Can an AI Agent Bypass Your Website Security? was first seen on Hacker News · Show HN on Nov 18, 2026. Since then it has appeared in 47 checks on 2 different days. Its best position was #7 of 30, reached on Nov 18, 17:52 UTC. It dropped off the list after Nov 19, 16:23 UTC.
Position on Hacker News · Show HN at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hacker News.
A few top-level comments from Hacker News, shortened. Read the full thread on Hacker News.
Really cool idea and working pretty good but I found some bug. For exemple I gave the landing page of my website which is accessible by default and it is show "at risk" because it can read the page. Also I am not sure about the "legal" part of this tool i think that you should add a message asking the authorization…
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 19, 16:23 UTC, after 2 days of trending.
#7 on Hacker News · Show HN, on Nov 18, 17:52 UTC. Trendoday checks this list every 30 minutes.
It was first seen on Nov 18, 2026 and has been on the list on 2 days (47 checks) since.
8 points and 1 comment; submitted by timshell on Nov 18, 2026.