# Perplexity finds most AI agents barely tested a VM's isolation in escape challenge

> Original title: Agents given the CTF prompt spent substantial effort hunting for the flag inside the VM, through files and services, rather than testing ...

- Source: Perplexity
- Published: 2026-11-11T18:21:30.000Z
- Bad Influence: https://badinfluence.news/items/jzxvifk3w5fbxsy9e3n3617nk
- Original: https://x.com/perplexity_ai/status/2120582707889795323

## Summary

Perplexity reports that when given a CTF prompt, AI agents spent most of their effort searching the VM for the flag through files and services rather than testing its isolation. Nine of 12 models spent at most 4% of their effort on the virtualization layer, so their failed escape attempts are weak evidence of the VM's security.

## Post

Agents given the CTF prompt spent substantial effort hunting for the flag inside the VM, through files and services, rather than testing the VM's isolation.

9 of 12 models spent at most 4% of their effort on the virtualization layer, so their failed escapes were weak evidence.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHW3SvBmasAAlu2z.png&mode=thumb&exp=1794787200&sig=0ff0f27f467adc80)