# Application Phishing

DevFeed: [Application Phishing](<https://devfeed.tech/articles/application-phishing-33425.md>)

Original publisher: [Read original article](<https://timkellogg.me/blog/2024/01/11/application-phishing>)

Published: 2024-01-11T00:00:00Z

Content type: opinion

Language: en

Sources: [Tim Kellogg](<https://devfeed.tech/sources/tim-kellogg.md>)

Topics: [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [Security](<https://devfeed.tech/topics/security.md>), [Social engineering](<https://devfeed.tech/topics/social-engineering.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [App](<https://devfeed.tech/topics/app.md>)

Tags: [llm](<https://devfeed.tech/tags/llm.md>), [phishing](<https://devfeed.tech/tags/phishing.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [security](<https://devfeed.tech/tags/security.md>), [social-engineering](<https://devfeed.tech/tags/social-engineering.md>)

## AI overview

The article argues that "prompt injection" is a misleading term for attacks that use language to make an LLM perform harmful behavior. It proposes "Application Phishing" because the application itself is the target, and contrasts the problem with SQL injection and social engineering.

## Source excerpt

"Prompt injection" is a perilously misleading term, we need a better phrase for it that helps beginners intuitively understand what's going on.