Ideas Weave Every Narrative with AI.
We are trained to fear links and attachments in emails. But the real danger is invisible. CSS—the innocent styling code used to make emails look good—is being weaponized to exfiltrate your data and track your behavior without you ever clicking a thing. Your inbox is no longer a safe space.
Atlassian Rovo’s URL retrieval tool has zero validation or access controls, letting attackers trick the AI into exfiltrating sensitive data through crafted URLs. But the real story isn’t the bug — it’s a fundamental design failure where Atlassian prioritized shipping an AI agent over basic security, assuming autonomous agents could safely handle internal data without human oversight. Every organization using Jira or Confluence with Rovo enabled is at risk.
CSS can silently leak text from your web page without any JavaScript. Using advanced selectors like :has(), attackers can query text nodes and exfiltrate data through background images or font loads. This technique bypasses traditional protections and turns the browser’s rendering engine into a spy. Developers must treat CSS as an active security threat.