--- title: "Superhuman AI Exfiltrates Emails" url: https://daily.dev/posts/superhuman-ai-exfiltrates-emails-edfs33r2w source_url: https://www.promptarmor.com/resources/superhuman-ai-exfiltrates-emails type: article source: "Hacker News" published: 2026-01-13T23:23:20.769Z updated: 2026-01-13T23:23:43.340Z tags: ["ai", "security", "vulnerability", "prompt-injection", "data-exfiltration"] reading_time: 9 upvotes: 2 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. # Superhuman AI Exfiltrates Emails **[Hacker News](https://daily.dev/sources/hn)** · 9 min read · 2 upvotes · 0 comments ## Summary Security researchers discovered critical prompt injection vulnerabilities in Superhuman AI that allowed attackers to exfiltrate sensitive emails without user interaction. By embedding malicious prompts in emails, attackers could manipulate the AI to extract financial, legal, and medical data from users' inboxes and submit it to attacker-controlled Google Forms. The attack exploited Superhuman's Content Security Policy whitelist for Google Docs and used Markdown image rendering to trigger automatic data submission. Similar zero-click vulnerabilities were found in Superhuman Go and Grammarly. Superhuman responded quickly, disabling vulnerable features and deploying remediation patches within days of disclosure. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Best of 2025: Google Gemini AI Flaw Could Lead to Gmail Compromise, Phishing](https://daily.dev/posts/best-of-2025-google-gemini-ai-flaw-could-lead-to-gmail-compromise-phishing-2c7ar72su) · Security Boulevard · 0 upvotes · 0 comments - [Hidden Prompts Trick AI Into False Email Summaries](https://daily.dev/posts/hidden-prompts-trick-ai-into-false-email-summaries-hemrpxxim) · Dark Reading · 0 upvotes · 0 comments - [When Email Speaks to Machines](https://daily.dev/posts/when-email-speaks-to-machines-tdcjsmpjk) · InfoSec Write-ups · 0 upvotes · 0 comments --- Tags: [#ai](https://daily.dev/tags/ai), [#security](https://daily.dev/tags/security), [#vulnerability](https://daily.dev/tags/vulnerability), [#prompt-injection](https://daily.dev/tags/prompt-injection), [#data-exfiltration](https://daily.dev/tags/data-exfiltration) [View this post on daily.dev](https://daily.dev/posts/superhuman-ai-exfiltrates-emails-edfs33r2w)