--- title: "Somebody told DeepSeek to build in-browser ransomware and it gleefully complied" url: https://daily.dev/posts/somebody-told-deepseek-to-build-in-browser-ransomware-and-it-gleefully-complied-grygc4fbm source_url: https://www.theregister.com/security/2026/07/01/somebody-told-deepseek-to-build-in-browser-ransomware-and-it-gleefully-complied/5265311 type: article source: "The Register" published: 2026-07-01T20:01:43.320Z updated: 2026-07-01T20:02:02.372Z tags: ["security", "ransomware", "deepseek"] reading_time: 3 upvotes: 0 comments: 0 language: 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. # Somebody told DeepSeek to build in-browser ransomware and it gleefully complied **[The Register](https://daily.dev/sources/theregister)** · 3 min read · 0 upvotes · 0 comments ## Summary A researcher from Check Point demonstrated that DeepSeek, a large language model, can be prompted to generate functional in-browser ransomware with minimal effort. The incomplete sample produced by DeepSeek could be transformed into a fully working attack, raising serious concerns about AI models being exploited to lower the barrier for creating malware. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [The crazy, true story behind the first AI-powered ransomware](https://daily.dev/posts/the-crazy-true-story-behind-the-first-ai-powered-ransomware-o8kptjiu3) · The Register · 0 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#ransomware](https://daily.dev/tags/ransomware), [#deepseek](https://daily.dev/tags/deepseek) [View this post on daily.dev](https://daily.dev/posts/somebody-told-deepseek-to-build-in-browser-ransomware-and-it-gleefully-complied-grygc4fbm)