--- title: "WARNING: Copilot prompt injection" url: https://daily.dev/posts/warning-copilot-prompt-injection-pzyaixvil source_url: https://www.youtube.com/watch?v=1RGi9txfiLg type: video:youtube source: "David Bombal" published: 2026-06-08T18:16:17.610Z updated: 2026-06-08T18:16:35.866Z tags: ["security", "github", "ai-agents", "prompt-injection"] reading_time: 2 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. # WARNING: Copilot prompt injection **[David Bombal](https://daily.dev/sources/davidbombal)** · 2 min read · 0 upvotes · 0 comments ## Summary A demonstration by Radware shows how indirect prompt injection attacks can compromise AI agents like Microsoft Copilot. In the demo, hidden text is embedded in an Excel spreadsheet containing stock data. When a user asks Copilot to summarize the data and recommend a stock, the AI follows the hidden malicious instructions instead — recommending a stock planted by the attacker. The core problem is that AI agents cannot distinguish between legitimate user instructions and malicious injected commands, making them vulnerable to silent attacks that could expose passwords or manipulate decisions. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [AI prompt injection gets real — with macros the latest hidden threat](https://daily.dev/posts/ai-prompt-injection-gets-real-with-macros-the-latest-hidden-threat-janyvtdh0) · CSO Online · 0 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#github](https://daily.dev/tags/github), [#ai-agents](https://daily.dev/tags/ai-agents), [#prompt-injection](https://daily.dev/tags/prompt-injection) [View this post on daily.dev](https://daily.dev/posts/warning-copilot-prompt-injection-pzyaixvil)