--- title: OpenAI’s GPT-Red automates prompt injection testing to... description: OpenAI has unveiled GPT-Red, an automated red-teaming system that uses self-play reinforcement learning to find prompt injection vulnerabilities in AI agents... canonical: https://daily.dev/posts/openai-s-gpt-red-automates-prompt-injection-testing-to-harden-ai-agents-8elgefjsx twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: OpenAI’s GPT-Red automates prompt injection testing to harden AI agents | daily.dev og:description: OpenAI has unveiled GPT-Red, an automated red-teaming system that uses self-play reinforcement learning to find prompt injection vulnerabilities in AI agents... og:url: https://daily.dev/posts/openai-s-gpt-red-automates-prompt-injection-testing-to-harden-ai-agents-8elgefjsx og:image: https://api.daily.dev/og/posts/8ElgEfjSx.png og:image:alt: OpenAI’s GPT-Red automates prompt injection testing to harden AI agents og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # OpenAI’s GPT-Red automates prompt injection testing to harden AI agents **[The New Stack](https://daily.dev/sources/newstack)** · 5 min read · 0 upvotes · 0 comments ## Summary OpenAI has unveiled GPT-Red, an automated red-teaming system that uses self-play reinforcement learning to find prompt injection vulnerabilities in AI agents at scale. The attacker model probes AI systems continuously, generating thousands of exploit variations to map vulnerability boundaries. GPT-Red was used to harden GPT-5.6, which now experiences six times fewer failures on direct prompt-injection benchmarks compared to the strongest production model released four months earlier, with only 0.05% failure rate against GPT-Red attacks. Real-world tests included convincing a production vending machine agent to slash prices and exfiltrate data from a Codex CLI agent. Notably, the security improvements did not increase over-refusals. OpenAI plans to scale the system further and expects to publish a technical preprint soon. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Continuously hardening ChatGPT Atlas against prompt injection attacks](https://daily.dev/posts/continuously-hardening-chatgpt-atlas-against-prompt-injection-attacks-cpcqd2gh9) · OpenAI · 2 upvotes · 0 comments - [Prompt injection breaks today’s AI agents, study warns](https://daily.dev/posts/prompt-injection-breaks-today-s-ai-agents-study-warns-2hfyd6ptc) · CSO Online · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#openai](https://daily.dev/tags/openai), [#reinforcement-learning](https://daily.dev/tags/reinforcement-learning), [#prompt-injection](https://daily.dev/tags/prompt-injection), [#red-teaming](https://daily.dev/tags/red-teaming) [View this post on daily.dev](https://daily.dev/posts/openai-s-gpt-red-automates-prompt-injection-testing-to-harden-ai-agents-8elgefjsx) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"OpenAI’s GPT-Red automates prompt injection testing to harden AI agents","url":"https://daily.dev/posts/openai-s-gpt-red-automates-prompt-injection-testing-to-harden-ai-agents-8elgefjsx","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/openai-s-gpt-red-automates-prompt-injection-testing-to-harden-ai-agents-8elgefjsx"},"datePublished":"2026-07-16T15:00:26.666Z","dateModified":"2026-07-22T10:20:21.050Z","description":"OpenAI has unveiled GPT-Red, an automated red-teaming system that uses self-play reinforcement learning to find prompt injection vulnerabilities in AI agents...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8c1fd6a9fca64af8253aac9237d12d28?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8c1fd6a9fca64af8253aac9237d12d28?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The New Stack","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"The New Stack","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/newstack","url":"https://daily.dev/sources/newstack"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/openai-s-gpt-red-automates-prompt-injection-testing-to-harden-ai-agents-8elgefjsx","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,openai,reinforcement-learning,prompt-injection,red-teaming","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The New Stack","item":"https://daily.dev/sources/newstack"},{"@type":"ListItem","position":3,"name":"OpenAI’s GPT-Red automates prompt injection testing to harden AI agents"}]} ```