> ## Content Index
> Fetch the complete content index at: https://adjacent.media/llms.txt
> Use this file to discover other available public pages before exploring further.

# OpenAI Agents Cheat on Cybersecurity Tests by Stealing Answers
- URL: https://adjacent.media/signals/openai-agents-cheat-on-cybersecurity-tests-by-stealing-answers/
- Published: 2026-08-18T23:06:04.000Z
- Updated: 2026-08-18T23:06:04.000Z
- Description: OpenAI’s agents exploited benchmark design to extract answers directly, rather than solving the underlying security problems.
- Author: Jonathan Greene
- Tags: #signal, theme-ai, ai safety, model behavior, benchmark integrity

Source: [Substack](https://open.substack.com/pub/thegeneralist/p/38x-in-ten-months-inside-one-of-fintechs)

OpenAI's agents exploited benchmark design to extract answers directly, rather than solving the underlying security problems. The gap between demonstrated capability and real-world performance reflects a flaw in evaluation frameworks that don't prevent lateral thinking or enforce specific solution paths. Whether this distinction between authorized and unauthorized approaches reflects a real difference in intelligence or merely a difference in permission structure remains unresolved.