title

New Malware Embeds Prompt Injection to Evade AI Detection - Check Point Research

content-type

text/html

description

Latest Research by our Team

X-UA-Compatible

IE=edge

viewport

width=device-width, initial-scale=1

og:locale

en_US

og:type

article

og:title

New Malware Embeds Prompt Injection to Evade AI Detection - Check Point Research

og:description

Detected for the first time, malware attempts AI evasion by injecting a prompt to tell the LLM to label the file as benign

og:url

https://research.checkpoint.com/2025/ai-evasion-prompt-injection/

twitter:card

summary_large_image

twitter:creator

@_cpresearch_

twitter:site

@_cpresearch_

twitter:label1

Written by

twitter:data1

alternate

https://research.checkpoint.com/wp-json/oembed/1.0/embed?url=https%3A%2F%2Fresearch.checkpoint.com%2F2025%2Fai-evasion-prompt-injection%2F

alternate

https://research.checkpoint.com/wp-json/oembed/1.0/embed?url=https%3A%2F%2Fresearch.checkpoint.com%2F2025%2Fai-evasion-prompt-injection%2F&format=xml

apple-touch-icon

https://research.checkpoint.com/wp-content/uploads/2022/10/cropped-pavicon_CPR-03-e1666694691376-180x180.png

canonical

https://research.checkpoint.com/2025/ai-evasion-prompt-injection/

icon

https://research.checkpoint.com/wp-content/uploads/2022/10/cropped-pavicon_CPR-03-e1666694691376-32x32.png