# GPT-Red: OpenAI's Internal Model for Testing Prompt-Injection Defenses

DevFeed: [GPT-Red: OpenAI's Internal Model for Testing Prompt-Injection Defenses](<https://devfeed.tech/articles/gpt-red-openai-is-training-models-to-break-other-models-28521.md>)

Original publisher: [Read original article](<https://blog.risingstack.com/gpt-red-openai-self-improving-ai-security/>)

Author: RisingStack Engineering

Published: 2026-07-16T13:05:35Z

Content type: opinion

Language: en

Sources: [RisingStack](<https://devfeed.tech/sources/risingstack.md>)

Topics: [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [ai safety](<https://devfeed.tech/topics/ai-safety.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-safety](<https://devfeed.tech/tags/ai-safety.md>), [openai](<https://devfeed.tech/tags/openai.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [red-teaming](<https://devfeed.tech/tags/red-teaming.md>)

## AI overview

The article explains indirect prompt injection and discusses GPT-Red, an internal OpenAI red-teaming model trained to attack other AI models, mainly through prompt injection. It argues that application permissions and tool access are important factors in the resulting security risk.

## Source excerpt

Prompt injection is still one of the least comfortable problems in AI development. You can improve your system prompt, restrict tools, validate outputs, and add approval steps before sensitive actions. Still, the model eventually has to read data you do not control. It might browse a webpage, process an email, inspect a repository, or use [...] The post GPT-Red: OpenAI Is Training Models to Break Other Models appeared first on RisingStack Engineering.